© 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. 60496
    Prev
    Next
    INDEX
    Explanations

    legal case citations

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

    This neuron fires on the numeric parts of legal case citations—court‐report volume and page numbers, docket and year references.

    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
    Ellie
    -0.76
     uta
    -0.72
     Bowling
    -0.69
    COLN
    -0.68
    rüstung
    -0.68
    望着
    -0.66
     ужа
    -0.66
    Merry
    -0.65
    ühner
    -0.64
    &.
    -0.63
    POSITIVE LOGITS
    STANDARD
    0.82
    CAPIT
    0.79
    Veel
    0.76
    杈
    0.75
    쌉
    0.74
     FREE
    0.73
    IBar
    0.72
     partition
    0.72
     vicin
    0.72
    fait
    0.71
    Activations Density 0.050%

    No Known Activations