© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58126
    Prev
    Next
    INDEX
    Explanations

    making a commitment

    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
    Negative Logits
    说起
    -1.73
    zzlement
    -1.57
     if
    -1.55
    "));
    -1.50
    %"),
    -1.46
    ❮
    -1.44
     jestli
    -1.42
     étrange
    -1.42
     обои
    -1.41
    );
    -1.40
    POSITIVE LOGITS
    ted
    1.70
     such
    1.45
    li
    1.41
    事項
    1.40
    er
    1.37
    pped
    1.36
    </b>
    1.35
    aperto
    1.35
    Схема
    1.33
    an
    1.32
    Activations Density 0.019%

    No Known Activations