© 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. 73538
    Prev
    Next
    INDEX
    Explanations

    names with initial-like tokens

    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
     in
    -2.30
     as
    -2.09
     on
    -1.98
     for
    -1.93
     at
    -1.91
    ;
    -1.88
     by
    -1.77
     from
    -1.71
     also
    -1.68
     will
    -1.66
    POSITIVE LOGITS
     réfrig
    1.66
    ఽ
    1.62
     impec
    1.59
     aranha
    1.56
    ſſen
    1.55
    鳚
    1.53
    actéristi
    1.53
     catég
    1.52
     insanely
    1.50
     équipements
    1.49
    Activations Density 0.126%

    No Known Activations