© 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. 119820
    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
     hvad
    -1.02
     Söhne
    -0.97
     poets
    -0.97
     caramel
    -0.95
     will
    -0.94
     mennes
    -0.94
     puisqu
    -0.94
     dashing
    -0.94
     comentário
    -0.94
     inclination
    -0.93
    POSITIVE LOGITS
    ⋁
    0.94
     学園
    0.93
     nhanh
    0.84
     lived
    0.84
    ブリッド
    0.82
     riso
    0.82
     erwerben
    0.82
     recomendamos
    0.81
    Confidence
    0.80
     bloß
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.