© 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. 22-GEMMASCOPE-RES-131K
    7. 127855
    Prev
    Next
    INDEX
    Explanations

    The neuron detects legal party designations in court case headings (e.g. “Plaintiff,” “Plaintiffs,” “Third-Party Plaintiffs”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    legal party designations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <eos>
    -2.38
    ."
    -0.98
     and
    -0.90
    」。
    -0.87
    』。
    -0.86
    ”。
    -0.82
    ↵↵↵↵↵↵↵↵
    -0.81
    </blockquote>
    -0.79
     will
    -0.79
    ↵↵↵↵
    -0.77
    POSITIVE LOGITS
    IJ
    0.99
     Toutefois
    0.99
     havet
    0.91
    HOE
    0.89
     diced
    0.89
     Certains
    0.88
     Hingga
    0.88
    お好み
    0.86
    美味しそう
    0.86
    Élet
    0.85
    Activations Density 0.151%

    No Known Activations