© 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. 21587
    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
    níky
    -0.90
     requerida
    -0.90
     canine
    -0.90
    されてる
    -0.90
     идут
    -0.89
     katk
    -0.89
     onları
    -0.88
    vlá
    -0.88
    عدم
    -0.88
    cassert
    -0.87
    POSITIVE LOGITS
     ucran
    0.91
     many
    0.89
    greens
    0.87
     Arboretum
    0.85
     historien
    0.84
    ्ञ
    0.83
     quedo
    0.81
     ткани
    0.81
    נו
    0.81
     bordo
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.