© 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. 58387
    Prev
    Next
    INDEX
    Explanations

    closing parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    and
    -1.83
    \
    -1.81
     of
    -1.80
    事も
    -1.70
    ate
    -1.68
    providedIn
    -1.68
    //
    -1.67
     以
    -1.66
    dzić
    -1.63
    Життє
    -1.63
    POSITIVE LOGITS
     entornos
    2.05
     was
    2.00
     they
    1.96
     anfitrión
    1.88
     hígado
    1.85
     sesiones
    1.84
     alrededores
    1.84
     bocetos
    1.84
    牁
    1.78
     cuando
    1.77
    Activations Density 0.001%

    No Known Activations