© 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. 4247
    Prev
    Next
    INDEX
    Explanations

    court case documents with Pennsylvania names

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

    The neuron detects fully capitalized tokens in legal document headers and case citations (e.g. jurisdiction names, party names, and section labels).

    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
     Idaho
    -0.89
    Показать
    -0.84
    ниях
    -0.82
    lación
    -0.81
     amanecer
    -0.81
     adiabatic
    -0.77
    有问题
    -0.77
     paciencia
    -0.77
     rendimiento
    -0.76
    瞠
    -0.76
    POSITIVE LOGITS
     Allentown
    1.02
     Lehigh
    0.82
     Berks
    0.77
     Janvier
    0.77
     Lieber
    0.77
     group
    0.76
    되어
    0.76
     attribu
    0.73
    containers
    0.73
     Harrisburg
    0.73
    Activations Density 0.010%

    No Known Activations