© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73696
    Prev
    Next
    INDEX
    Explanations

    federal supplement citations

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

    This neuron detects law-reporter citations in the “Federal Supplement” format—i.e. volume numbers, the “F. Supp.” reporter abbreviation, and the parenthesized year.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     our
    -1.26
     your
    -1.13
    }
    -0.98
    赏
    -0.85
     features
    -0.84
     queryParams
    -0.83
    ֩
    -0.79
     unseren
    -0.78
    '])){
    -0.77
     Empieza
    -0.76
    POSITIVE LOGITS
    ּוֹ
    1.12
    ֑
    1.07
    ಲ್ಲಿ
    1.07
    thée
    1.02
    chymal
    0.98
    іе
    0.97
    chement
    0.96
     aufgestellt
    0.96
    deauna
    0.96
    ană
    0.96
    Activations Density 0.212%

    No Known Activations