© 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. 13996
    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
     it
    -1.62
    我一
    -1.29
    UCIÓN
    -1.27
     некото
    -1.25
     Verlauf
    -1.23
     Durchsch
    -1.22
    沨
    -1.21
    lifford
    -1.20
    出一
    -1.17
    有助
    -1.17
    POSITIVE LOGITS
     pengar
    1.61
     fald
    1.46
     boya
    1.45
    猻
    1.43
     kazak
    1.43
     ACKNOWLEDGMENTS
    1.42
    不可思议
    1.41
     perioden
    1.38
     kado
    1.38
     magasiner
    1.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.