© 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. 10-GEMMASCOPE-RES-131K
    7. 9814
    Prev
    Next
    INDEX
    Explanations

    legal case citations

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

    This neuron detects numeric citations and page or docket numbers (e.g. margin or slip-op numbers) in legal opinions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    {
    -2.11
    鹪
    -2.03
     graced
    -1.95
     lorsque
    -1.91
    enablog
    -1.91
    
    -1.89
    酡
    -1.89
    ఽ
    -1.82
     城市
    -1.82
    erializer
    -1.82
    POSITIVE LOGITS
    c
    2.48
     unparalleled
    1.98
    h
    1.95
     innumerable
    1.88
    f
    1.85
    烔
    1.84
     numerous
    1.80
     noteworthy
    1.74
     incessant
    1.74
    t
    1.73
    Activations Density 0.020%

    No Known Activations