© 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. 14190
    Prev
    Next
    INDEX
    Explanations

    washington D.C. and state entities

    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
    絰
    -2.86
    自己
    -2.84
    鵙
    -2.66
    樒
    -2.63
     สาม
    -2.58
    说
    -2.50
     dà
    -2.50
    导致
    -2.47
    的
    -2.47
    他的
    -2.45
    POSITIVE LOGITS
    ↵
    3.25
    轫
    3.00
    ).”
    2.95
    .’”
    2.95
    .'”
    2.80
    ”;
    2.78
     Our
    2.69
    肫
    2.64
    ”.
    2.58
    ↵↵
    2.56
    Activations Density 0.008%

    No Known Activations