© 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. 129093
    Prev
    Next
    INDEX
    Explanations

    foreground color

    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
    </i>
    -2.17
    </b>
    -2.09
    there
    -1.99
    تیجه
    -1.91
    не
    -1.86
    我们
    -1.85
    \
    -1.84
    你
    -1.77
    EN
    -1.70
    -
    -1.69
    POSITIVE LOGITS
    '
    2.36
     of
    2.09
    ⑊
    1.91
     asserting
    1.85
    踟
    1.82
    鷙
    1.78
    ⁛
    1.77
     вернулся
    1.75
    愎
    1.75
     ahşap
    1.74
    Activations Density 0.006%

    No Known Activations