© 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. 3220
    Prev
    Next
    INDEX
    Explanations

    software license or documentation

    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
    Ω
    -0.83
    usten
    -0.78
    Proposition
    -0.76
     Ω
    -0.75
    Ν
    -0.75
     πο
    -0.73
    OBJ
    -0.73
    findViewById
    -0.73
     plo
    -0.72
    kiat
    -0.72
    POSITIVE LOGITS
     bár
    0.77
    間に
    0.75
     keyPressed
    0.72
     fournisse
    0.72
     wicker
    0.71
     pageNum
    0.71
    ixa
    0.69
     Stimm
    0.69
    Acknowled
    0.67
     aimez
    0.67
    Activations Density 0.022%

    No Known Activations