© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39903
    Prev
    Next
    INDEX
    Explanations

    Oxford University

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    甃
    -2.33
     Of
    -2.25
    琑
    -2.13
     For
    -2.08
    鬭
    -2.00
    .}(
    -1.95
    %">
    -1.95
     Здесь
    -1.92
    Ⓔ
    -1.91
     we
    -1.91
    POSITIVE LOGITS
    s
    2.67
    ↵
    2.39
     nouvelles
    2.09
     dizzy
    1.97
     vü
    1.94
    你和
    1.87
    羁
    1.79
     regimen
    1.77
    躥
    1.74
    zij
    1.73
    Activations Density 0.009%

    No Known Activations