© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45365
    Prev
    Next
    INDEX
    Explanations

    function definitions and calls

    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
     autre
    -2.81
     botella
    -2.33
     pulsera
    -2.31
     baskılı
    -2.30
     pegatina
    -2.30
     parfüm
    -2.28
     vendeur
    -2.27
     chaqueta
    -2.27
     parfü
    -2.25
     sudadera
    -2.20
    POSITIVE LOGITS
    >
    2.05
    :
    1.92
     at
    1.91
     medusa
    1.84
     without
    1.82
    </h2>
    1.78
     vinaigrette
    1.77
     canad
    1.74
     There
    1.73
     to
    1.72
    Activations Density 0.002%

    No Known Activations