© 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. 33490
    Prev
    Next
    INDEX
    Explanations

    legal citations and company names

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

    This neuron detects legal‐citation markers, specifically volume and page numbers (and similar reporter references) in case 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
    chapters
    -0.87
     réforme
    -0.79
     洛
    -0.79
    stasy
    -0.79
    ACIO
    -0.79
    襦
    -0.79
     maail
    -0.77
     législation
    -0.77
    erevan
    -0.76
     hvorfor
    -0.76
    POSITIVE LOGITS
     at
    3.31
    Ở
    0.99
    rogens
    0.98
     tại
    0.94
     Kilo
    0.93
     kilo
    0.92
    rogenic
    0.90
     عند
    0.89
    于
    0.88
     στο
    0.88
    Activations Density 0.045%

    No Known Activations