© 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. 86297
    Prev
    Next
    INDEX
    Explanations

    court case citations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron identifies legal case citations to the Federal Reporter (volume number, “F.2d” abbreviation, and page reference).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    :
    -1.66
     may
    -1.59
     will
    -1.59
    ();
    -1.54
    ,
    -1.53
     also
    -1.50
     even
    -1.46
    };
    -1.45
    );
    -1.45
    //
    -1.45
    POSITIVE LOGITS
    смарт
    1.55
     famoso
    1.53
     этого
    1.52
    棡
    1.48
     modeli
    1.48
    想了想
    1.47
    拍了拍
    1.44
    叹了口气
    1.42
    ሺ
    1.41
     längere
    1.38
    Activations Density 0.042%

    No Known Activations