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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18062
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    emorrh
    0.50
     respiration
    0.46
    ü
    0.45
     Conversely
    0.44
    ndrome
    0.42
    IDs
    0.42
     WOM
    0.42
     palmit
    0.42
    ന്ത്രാ
    0.41
     outcome
    0.40
    POSITIVE LOGITS
    釈
    0.55
    غیر
    0.54
    ﻁ
    0.52
    ですが
    0.51
    ﻥ
    0.51
    غير
    0.47
    эта
    0.47
    మెంట్
    0.46
    लेकिन
    0.46
    労働
    0.46
    Activations Density 0.001%

    No Known Activations