© 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. 66410
    Prev
    Next
    INDEX
    Explanations

    html tags and code snippets

    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
     which
    -2.28
     Some
    -2.28
     at
    -2.08
     after
    -2.06
     from
    -1.95
     There
    -1.94
     of
    -1.88
    </i>
    -1.82
     by
    -1.81
     Surprisingly
    -1.80
    POSITIVE LOGITS
    ㄴ
    2.31
     
    1.98
     permettent
    1.95
    ¸
    1.92
    (,
    1.90
     rè
    1.84
    ‒
    1.80
    狴
    1.80
    ..........
    1.80
    $-$
    1.78
    Activations Density 0.003%

    No Known Activations