© 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. 130094
    Prev
    Next
    INDEX
    Explanations

    civil case citations

    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
    </em>
    -2.70
    趼
    -2.58
    </h3>
    -2.53
    鴣
    -2.33
    dámské
    -2.33
    jangan
    -2.27
    dientemente
    -2.23
    鳧
    -2.23
     være
    -2.23
    !”
    -2.23
    POSITIVE LOGITS
    是
    3.17
    m
    3.13
    "
    2.95
    𔘓
    2.81
    秾
    2.75
    ൮
    2.69
    料
    2.69
     we
    2.69
    k
    2.64
    s
    2.59
    Activations Density 0.004%

    No Known Activations