© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34979
    Prev
    Next
    INDEX
    Explanations

    code symbols and punctuation

    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
    RECOMM
    -0.86
    ishi
    -0.84
    ణ
    -0.75
     next
    -0.74
     jung
    -0.74
    欢
    -0.74
    ()){
    
    -0.73
    тий
    -0.72
    нами
    -0.72
    rome
    -0.72
    POSITIVE LOGITS
    küche
    0.82
    kön
    0.81
    🛤
    0.78
    ymbol
    0.77
    ToDate
    0.75
     toalla
    0.75
     kön
    0.75
    帰り
    0.74
    Oggi
    0.74
     Améli
    0.73
    Activations Density 0.001%

    No Known Activations