© 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. 22-GEMMASCOPE-RES-131K
    7. 129032
    Prev
    Next
    INDEX
    Explanations

    proposals ask

    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_22/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
    さぁ
    -2.08
    えっ
    -2.00
    あぁ
    -1.99
    にほんブログ村
    -1.97
    明日は
    -1.95
    つづく
    -1.91
    まさかの
    -1.88
    もうすぐ
    -1.87
    おわりに
    -1.84
    あー
    -1.80
    POSITIVE LOGITS
    ,
    1.94
     for
    1.68
    <bos>
    1.35
     other
    1.28
     (
    1.28
     in
    1.23
    e
    1.16
    ですが
    1.15
    がありますが
    1.13
    n
    1.13
    Activations Density 0.154%

    No Known Activations