© 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. 59133
    Prev
    Next
    INDEX
    Explanations

    LOS ANGELES

    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
    .”
    -2.41
    ſtra
    -2.22
    These
    -2.20
    os
    -2.19
    婬
    -2.16
    ୈ
    -2.09
     Frühjahr
    -2.08
    >
    -2.06
    onomies
    -1.99
    できるので
    -1.98
    POSITIVE LOGITS
     unſ
    2.30
    ’
    2.14
     Of
    2.08
    /';
    2.00
    糁
    1.91
    pulseira
    1.90
    <bos>
    1.90
     ſever
    1.84
    miques
    1.81
     obligación
    1.75
    Activations Density 0.005%

    No Known Activations