© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44276
    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
    釦
    -1.11
    看去
    -1.00
    Kirchen
    -0.94
     categorization
    -0.94
     gefähr
    -0.92
    半个
    -0.91
    嗬
    -0.90
    隕
    -0.89
    優雅
    -0.89
    Joueur
    -0.89
    POSITIVE LOGITS
     also
    1.16
    だそうです
    1.04
     anzeigen
    1.02
    breviation
    0.97
    يات
    0.96
     mecánica
    0.96
     pulumi
    0.96
     "];
    0.95
     Tamaño
    0.93
    ]";
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.