© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4674
    Prev
    Next
    INDEX
    Explanations

    This neuron is associated with sentence structure and completion, particularly marking the end or continuation of lists and code snippets.**Analysis:**1. **MAX_ACTIVATING_TOKENS**: Contains punctuation marks like `.` , `"` and symbols like `*`. These often appear at the end of sentences, list items, or within code blocks.2. **TOKENS_AFTER_MAX_ACTIVATING_TOKEN**: Includes words like `B`, `By`, `Predict`, `navigate`, `Chad`, and also symbols `*`, `2`. Some of these might be beginnings of new sentences, options (like 'B'), or continuations from the provided examples (like 'ChadGPT', 'navigate', 'Predict'). The presence of `B` could indicate options in a multiple-choice context.3.This neuron detects list items and sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cleaved
    0.56
     autoradi
    0.56
     domesticated
    0.55
     interdependent
    0.53
     prefabricated
    0.53
     extol
    0.53
     verand
    0.52
     extensible
    0.51
     deviates
    0.51
     substantiated
    0.50
    POSITIVE LOGITS
    ं
    0.54
    N
    0.52
    I
    0.50
     പ്രതീക്ഷ
    0.50
    V
    0.50
    ウィ
    0.49
    U
    0.47
    但
    0.47
    你好
    0.46
    S
    0.46
    Activations Density 9.648%

    No Known Activations