© 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. 90659
    Prev
    Next
    INDEX
    Explanations

    table set paint change Stretch

    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
    ้าว
    -0.80
    Swatch
    -0.77
    мери
    -0.76
     pasangan
    -0.74
    佃
    -0.71
    dflare
    -0.71
     Belg
    -0.70
    天道
    -0.69
    ISTRATION
    -0.69
     panels
    -0.68
    POSITIVE LOGITS
    getTable
    0.97
     JTable
    0.95
    モデル
    0.92
     table
    0.91
     Table
    0.89
    Table
    0.88
     행
    0.81
    setModel
    0.79
     Tisch
    0.78
     ménages
    0.76
    Activations Density 0.001%

    No Known Activations