© 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. 89832
    Prev
    Next
    INDEX
    Explanations

    Rule, appcompat, development, communication

    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
     down
    -0.77
    bản
    -0.76
    ternos
    -0.75
     modificación
    -0.75
    haway
    -0.74
    ストン
    -0.73
     prosty
    -0.72
     Technol
    -0.72
    haram
    -0.72
    нус
    -0.71
    POSITIVE LOGITS
     rule
    0.90
     registro
    0.86
     rules
    0.82
    Gef
    0.79
     сезо
    0.75
    viez
    0.73
    وذ
    0.73
    idium
    0.73
    fontStyle
    0.71
    rtner
    0.71
    Activations Density 0.003%

    No Known Activations