© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13191
    Prev
    Next
    INDEX
    Explanations

    future options

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron lights up on semantically rich content words (e.g. uncommon nouns, verbs, and adjectives) rather than on high-frequency function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ва
    0.87
    و
    0.85
     económico
    0.81
    ocarcinoma
    0.80
    рда
    0.79
    ﻭ
    0.77
    🐣
    0.77
    났
    0.77
    addImage
    0.75
    newToken
    0.74
    POSITIVE LOGITS
     nomenclature
    0.81
     Ashok
    0.79
     hallway
    0.77
     receipt
    0.77
     finesse
    0.77
     succinctly
    0.76
     topology
    0.74
     measurement
    0.74
    ‌ترین
    0.74
    رفة
    0.73
    Activations Density 0.001%

    No Known Activations