© 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. 115555
    Prev
    Next
    INDEX
    Explanations

    legal citations and licenses

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

    This neuron detects tokens that appear in legal‐document headers and citations (e.g. court names, docket/report numbers, dates, and volume/page references).

    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
     jealous
    -0.84
     nær
    -0.76
     Jealous
    -0.75
     workloads
    -0.73
    Loire
    -0.72
    opardi
    -0.71
    Etymology
    -0.70
    Workload
    -0.70
    Jealous
    -0.69
     polyps
    -0.69
    POSITIVE LOGITS
    entity
    0.87
    ough
    0.78
    orders
    0.73
    integrated
    0.71
    inv
    0.70
    bela
    0.66
    pea
    0.66
    椅
    0.66
    dex
    0.65
    vertex
    0.65
    Activations Density 0.100%

    No Known Activations