© 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. 74148
    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
    onya
    -0.96
     clog
    -0.95
     доме
    -0.95
    回了
    -0.95
     unrecognized
    -0.94
     quarantine
    -0.93
     ήταν
    -0.90
    mol
    -0.90
    RemoveAt
    -0.90
    EH
    -0.89
    POSITIVE LOGITS
     to
    0.96
     Kommentare
    0.92
     publicó
    0.89
    是個
    0.88
     réservés
    0.88
    ->$
    0.88
     nació
    0.87
     这
    0.87
     electrico
    0.84
     хоте
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.