© 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. 10-GEMMASCOPE-RES-131K
    7. 102427
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ganz
    -1.31
    vau
    -0.96
     tisíc
    -0.93
    stopp
    -0.92
     mengucap
    -0.92
    caixa
    -0.91
     dadas
    -0.91
     jelasnya
    -0.91
    勦
    -0.90
     lika
    -0.90
    POSITIVE LOGITS
    etí
    1.03
     Punj
    0.90
    ละ
    0.90
    [
    0.88
    ores
    0.88
    珈琲
    0.86
    Dichlorobenzene
    0.86
    記事
    0.86
     Equations
    0.85
     Badezimmer
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.