© 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. 99354
    Prev
    Next
    INDEX
    Explanations

    opening angle brackets

    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
     This
    -2.34
     Whether
    -2.05
     since
    -1.82
     and
    -1.77
     Lately
    -1.66
     If
    -1.63
     Especially
    -1.63
    ,
    -1.60
    ⼈
    -1.56
    殃
    -1.55
    POSITIVE LOGITS
    '
    2.38
    あぁ
    1.95
    别人的
    1.90
     participe
    1.89
    </h5>
    1.88
    まさかの
    1.85
    えっ
    1.84
    ほんとに
    1.84
    やっぱ
    1.82
    関連リンク
    1.81
    Activations Density 0.015%

    No Known Activations