© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93377
    Prev
    Next
    INDEX
    Explanations

    dissent, diss, dissenting

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

    This neuron detects legal citation markers, especially numeric references (volumes, page numbers, case numbers) in court‐opinion headings and citations.

    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
     прось
    -0.77
    妪
    -0.75
     meliputi
    -0.71
    ENTA
    -0.68
    राब
    -0.67
    antuan
    -0.67
    IDAY
    -0.67
     restera
    -0.67
    zhu
    -0.66
    dication
    -0.66
    POSITIVE LOGITS
     dissent
    4.31
     dissenting
    4.09
     diss
    3.47
     Diss
    2.94
     Dissent
    2.91
    Diss
    2.70
    diss
    2.50
     dissen
    2.33
     DISS
    2.33
     minority
    2.17
    Activations Density 0.048%

    No Known Activations