© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60475
    Prev
    Next
    INDEX
    Explanations

    gears, gearboxes, and shifting

    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
    棐
    -2.13
    鯔
    -2.09
     eſſ
    -2.09
    咈
    -2.03
    ズニー
    -2.03
    ेमाल
    -1.92
    ⡪
    -1.91
    脔
    -1.89
    Новые
    -1.89
     verdure
    -1.86
    POSITIVE LOGITS
    '
    2.53
     are
    2.02
    }$
    1.91
    );
    1.89
     [
    1.88
     случаев
    1.83
     the
    1.80
     *
    1.77
    都有
    1.77
     Перейти
    1.73
    Activations Density 0.019%

    No Known Activations