© 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. 60510
    Prev
    Next
    INDEX
    Explanations

    post prefix

    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
     information
    -0.77
     purify
    -0.77
    鵺
    -0.75
     სა
    -0.75
    文獻
    -0.73
     (){
    -0.72
    IVEREF
    -0.69
     infiltrate
    -0.68
     timeframe
    -0.68
    セミナー
    -0.68
    POSITIVE LOGITS
    pyplot
    0.93
    Æ
    0.89
    transcription
    0.85
     prowess
    0.82
    (*
    0.79
    classic
    0.79
     обрабаты
    0.78
    Arn
    0.78
    '$
    0.76
    ween
    0.75
    Activations Density 0.046%

    No Known Activations