© 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. 90052
    Prev
    Next
    INDEX
    Explanations

    court cases and legal documents

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

    The neuron fires strongly on the structured metadata of legal opinions—case numbers, citations, party abbreviations, court names, and related docket identifiers.

    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
     オフ
    -0.81
     المك
    -0.79
    pari
    -0.79
    сии
    -0.75
     بإ
    -0.75
    hint
    -0.74
     Fahrer
    -0.72
    Charge
    -0.71
    δή
    -0.70
     Transcript
    -0.69
    POSITIVE LOGITS
    Ehr
    0.77
    渓
    0.70
    семь
    0.69
     Toms
    0.68
     pry
    0.67
    SafeMath
    0.67
     plenamente
    0.67
    withstanding
    0.66
     McDonnell
    0.66
    deta
    0.65
    Activations Density 0.017%

    No Known Activations