© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129860
    Prev
    Next
    INDEX
    Explanations

    This neuron detects legal case citations (the “X v Y” headings with associated volume, reporter, year, court, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    legal case citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     "@
    -1.18
     бю
    -1.14
     творо
    -1.13
    eleste
    -1.10
     ἄ
    -1.08
    мый
    -1.07
    ınıza
    -1.06
     Computed
    -1.05
     négoci
    -1.05
    ֺ
    -1.05
    POSITIVE LOGITS
     cases
    1.70
     célèbre
    1.48
     белого
    1.37
     famous
    1.33
     case
    1.33
     любого
    1.31
     famously
    1.30
     was
    1.30
    ühen
    1.30
     when
    1.29
    Activations Density 0.041%

    No Known Activations