© 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. 7227
    Prev
    Next
    INDEX
    Explanations

    legal citations

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

    The neuron fires on sequences of numbers used in legal case citations and dates (e.g. volume and page numbers, years, docket numbers).

    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
    cję
    -0.78
     Deeds
    -0.77
    ATIVES
    -0.77
     settembre
    -0.76
     butternut
    -0.76
    ➦
    -0.75
     quince
    -0.75
    十三
    -0.75
     there
    -0.75
     methanol
    -0.75
    POSITIVE LOGITS
     upheld
    1.11
     uphold
    1.04
     upholding
    1.00
     landmark
    0.96
     Supreme
    0.85
     case
    0.84
     dhe
    0.79
    蒸し
    0.78
     uży
    0.76
    cardname
    0.75
    Activations Density 0.078%

    No Known Activations