© 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. 34-GEMMASCOPE-RES-131K
    7. 117943
    Prev
    Next
    INDEX
    Explanations

    appellate court districts

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

    The neuron selectively activates on legal‐citation formatting—particularly numeric references such as volume and reporter numbers, docket or case numbers, and parenthesized year or court identifiers typical of 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
     granos
    -0.82
     conseguenze
    -0.74
     Burch
    -0.74
    ihnachts
    -0.73
    iners
    -0.73
     pressure
    -0.71
    UpdateDate
    -0.70
    distributed
    -0.68
     oog
    -0.68
    inerario
    -0.68
    POSITIVE LOGITS
     First
    0.94
     Third
    0.90
     Fourth
    0.88
    Earn
    0.78
    Pere
    0.72
     Fifth
    0.70
     диви
    0.69
    Third
    0.69
    秋田
    0.68
     спра
    0.68
    Activations Density 0.267%

    No Known Activations