© 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. 84210
    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
     такого
    -0.93
     experimenta
    -0.91
    imetsu
    -0.90
    erves
    -0.90
     secession
    -0.88
     Condiciones
    -0.88
    这样一个
    -0.87
    ufes
    -0.87
    leding
    -0.87
     veja
    -0.87
    POSITIVE LOGITS
    ycznie
    0.98
    {@
    0.97
     авгу
    0.97
     heapq
    0.96
     fortfarande
    0.95
    ۔
    0.93
    
    0.91
     Italie
    0.90
    ble
    0.90
     Pradesh
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.