© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15832
    Prev
    Next
    INDEX
    Explanations

    book titles and descriptions

    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_40_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
    Run
    0.45
    Res
    0.43
    Len
    0.43
    Ze
    0.42
    Ron
    0.41
    Twilight
    0.40
     Run
    0.40
    a
    0.40
    Fan
    0.40
    Jack
    0.39
    POSITIVE LOGITS
     Reprinted
    0.55
     Audiobook
    0.54
     അല്ലെങ്കിൽ
    0.50
     Yayın
    0.50
     Annotated
    0.48
     ឬ
    0.48
     reprinted
    0.46
    ∓
    0.45
     Translated
    0.45
    лектрон
    0.45
    Activations Density 0.003%

    No Known Activations