© 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. 1377
    Prev
    Next
    INDEX
    Explanations

    court case citations

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

    The neuron fires on numeric and reporter‐citation tokens (volumes, page numbers, and court‐reporter abbreviations) in legal case citations.

    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
    multirow
    -0.77
    豔
    -0.75
     Walkthrough
    -0.75
    取る
    -0.75
     chamber
    -0.71
     lahko
    -0.71
     Chamber
    -0.70
    風險
    -0.69
     Uphol
    -0.69
     Capítulo
    -0.69
    POSITIVE LOGITS
    飢
    0.77
    orique
    0.73
    uestran
    0.73
    imagine
    0.72
     setzt
    0.72
    Stra
    0.72
    ukas
    0.72
    ومات
    0.71
    Filed
    0.70
     Oba
    0.70
    Activations Density 0.086%

    No Known Activations