© 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. 128316
    Prev
    Next
    INDEX
    Explanations

    to people receiving care

    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
    '
    -2.52
     that
    -1.86
     some
    -1.70
     adding
    -1.62
     maybe
    -1.62
     perhaps
    -1.54
     after
    -1.51
     having
    -1.49
     preparing
    -1.49
     one
    -1.47
    POSITIVE LOGITS
     "";
    1.90
    Ꮗ
    1.88
    </h5>
    1.86
    푙
    1.84
    轵
    1.80
    leggio
    1.77
     griego
    1.74
     هذا
    1.73
    Tại
    1.73
     från
    1.71
    Activations Density 0.037%

    No Known Activations