© 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. 34-GEMMASCOPE-RES-131K
    7. 29987
    Prev
    Next
    INDEX
    Explanations

    legal citation punctuation

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

    The neuron strongly activates on strings of digits and punctuation used in legal citations—i.e. volume, reporter, docket, and page numbers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    UpInside
    -0.91
    ניה
    -0.83
     mondo
    -0.82
    які
    -0.82
    Offic
    -0.82
     bicy
    -0.79
     البعض
    -0.79
    сим
    -0.78
     Öffentlichkeit
    -0.78
    ściej
    -0.78
    POSITIVE LOGITS
     consommateurs
    0.88
    などは
    0.83
     supra
    0.81
    總結
    0.79
     хорошая
    0.78
     logements
    0.76
    ネットで
    0.76
     Верхов
    0.75
     Мен
    0.74
    Oacute
    0.73
    Activations Density 0.101%

    No Known Activations