© 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. 58413
    Prev
    Next
    INDEX
    Explanations

    log file paths and decoders

    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
     Haver
    -0.89
     REPORTING
    -0.86
    を変更
    -0.77
     Tuttle
    -0.77
    重的
    -0.77
    messenger
    -0.75
     Reporting
    -0.75
     metabolismo
    -0.74
     sentimento
    -0.74
    ciato
    -0.74
    POSITIVE LOGITS
    search
    0.87
     stream
    0.81
    Search
    0.77
    lines
    0.77
    grep
    0.75
    stream
    0.75
     Search
    0.74
     search
    0.73
    gte
    0.73
    chial
    0.72
    Activations Density 0.015%

    No Known Activations