© 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. 128745
    Prev
    Next
    INDEX
    Explanations

    enduring effects

    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
     morceaux
    -2.66
     victoires
    -2.64
     doigts
    -2.48
    鏐
    -2.45
     oreilles
    -2.30
     rempliss
    -2.30
    鈈
    -2.27
    ugeot
    -2.25
    ᐠ
    -2.23
     jambes
    -2.22
    POSITIVE LOGITS
    an
    2.97
    );
    2.91
     see
    2.63
    in
    2.59
    re
    2.50
    </h2>
    2.39
    A
    2.39
    ke
    2.34
    </em>
    2.33
    wa
    2.33
    Activations Density 0.004%

    No Known Activations