© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41001
    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
    fileprivate
    -0.99
     Seil
    -0.97
    าม
    -0.89
     объема
    -0.88
    êque
    -0.88
    ℯ
    -0.87
     диапа
    -0.87
    ノン
    -0.87
     Total
    -0.86
    anci
    -0.86
    POSITIVE LOGITS
    bestos
    1.09
     zowel
    1.04
    '*
    1.04
    örung
    1.01
    kinds
    0.99
    /¯
    0.99
     eenen
    0.98
     fizeram
    0.96
     gegevens
    0.95
     biedt
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.