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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2388
    Prev
    Next
    INDEX
    Explanations

    free software

    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
    DECL
    -0.84
    保管
    -0.73
    uso
    -0.72
    垂直
    -0.71
     Larry
    -0.67
     decl
    -0.66
    zący
    -0.66
    挪
    -0.66
    VERT
    -0.66
    lanca
    -0.65
    POSITIVE LOGITS
    included
    0.73
    eventually
    0.71
    選べる
    0.71
    empre
    0.70
    elseif
    0.69
     AHEAD
    0.69
    boiler
    0.68
    見ると
    0.68
     सामान
    0.68
    考虑到
    0.67
    Activations Density 0.045%

    No Known Activations