© 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. 34-GEMMASCOPE-RES-131K
    7. 58278
    Prev
    Next
    INDEX
    Explanations

    title, on, line, number

    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_34/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
    ubes
    -0.77
    SELL
    -0.75
     ILL
    -0.70
    ęż
    -0.69
    Yg
    -0.69
    Ql
    -0.69
     documentaire
    -0.68
    quid
    -0.68
     PACE
    -0.68
    LUC
    -0.68
    POSITIVE LOGITS
    Comfort
    0.82
     want
    0.72
     Comfort
    0.72
     comfort
    0.70
     Immunol
    0.68
    viert
    0.67
     reckoned
    0.67
     комфорт
    0.65
    Function
    0.65
     greatest
    0.64
    Activations Density 0.054%

    No Known Activations