© 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. 22261
    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
     засо
    -0.96
    hounds
    -0.93
     “…
    -0.88
     halbe
    -0.88
     halben
    -0.86
     always
    -0.84
    when
    -0.84
    ну
    -0.84
    for
    -0.84
     those
    -0.83
    POSITIVE LOGITS
     וי
    1.01
     hablamos
    0.97
    Alp
    0.95
     despicable
    0.93
     ním
    0.90
     seulement
    0.89
    佐藤
    0.88
    Yue
    0.87
     مراجع
    0.87
    );
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.