© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62545
    Prev
    Next
    INDEX
    Explanations

    US court of appeals, patent cases

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

    The neuron is picking out the formal court‐opinion header (the caption block naming “United States Court of Appeals for the Federal Circuit,” case numbers, judges, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     し
    -0.78
    entennial
    -0.77
     ECS
    -0.69
    CHK
    -0.66
    EdgeInsets
    -0.64
     filmmaking
    -0.63
    ：(
    -0.63
    bory
    -0.63
    mitt
    -0.63
     filmmaker
    -0.63
    POSITIVE LOGITS
     patent
    1.66
     Patent
    1.62
    Patent
    1.54
     infringement
    1.51
     PATENT
    1.46
     Patents
    1.40
    patent
    1.37
     patente
    1.33
     patents
    1.30
     Inventors
    1.25
    Activations Density 0.211%

    No Known Activations