© 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. 34-GEMMASCOPE-RES-131K
    7. 64440
    Prev
    Next
    INDEX
    Explanations

    rule of procedure

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

    The neuron spotlights formal legal rule citations, especially references to civil procedure rules (e.g. “Texas Rules of Civil Procedure”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Debugging
    -0.76
    Ꮖ
    -0.75
     AMA
    -0.73
     efficacy
    -0.72
     Rés
    -0.72
    一颗
    -0.71
     Boeing
    -0.69
     thọ
    -0.69
    书记
    -0.69
     Huma
    -0.69
    POSITIVE LOGITS
     Procedure
    1.00
     procedure
    0.99
    procedure
    0.95
    Procedure
    0.91
     Procedures
    0.81
     Governing
    0.80
    CppMethod
    0.77
     przyzna
    0.73
    ]-\
    0.72
     процеду
    0.71
    Activations Density 0.045%

    No Known Activations