© 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. 10-GEMMASCOPE-RES-131K
    7. 61350
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Zalety
    -1.05
    vertra
    -1.04
    支付
    -0.94
    خوان
    -0.92
    always
    -0.91
     inaug
    -0.91
     rendre
    -0.90
     Sénat
    -0.89
    export
    -0.89
    锈钢
    -0.88
    POSITIVE LOGITS
    InputBorder
    1.04
     IOError
    0.93
    ใช้งาน
    0.91
     neighborhood
    0.89
    казать
    0.89
    rhosis
    0.84
     young
    0.83
     związku
    0.83
     líquidos
    0.83
    Ｚ
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.