© 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. 62795
    Prev
    Next
    INDEX
    Explanations

    Whitney and Whittaker names

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

    The neuron detects formal legal case citations (especially U.S. Supreme Court party names, reporter volume/page numbers, and the “v.” separator).

    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
     infan
    -0.78
    Giới
    -0.78
     sedikit
    -0.78
     prostitu
    -0.77
     lente
    -0.74
     stringBuilder
    -0.71
     $/
    -0.70
     cilind
    -0.69
     ortodo
    -0.69
     Apare
    -0.69
    POSITIVE LOGITS
    =-\
    0.82
     pokud
    0.78
     Shark
    0.77
    诶
    0.74
     Від
    0.73
    olfo
    0.73
     inicialmente
    0.72
     моя
    0.71
     akce
    0.71
    isons
    0.71
    Activations Density 0.017%

    No Known Activations