© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16394
    Prev
    Next
    INDEX
    Explanations

    legal case citations

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

    The neuron activates on numeric tokens in legal citations—i.e. volume, page, year, and 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_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
     været
    -1.65
    éroport
    -1.45
     kimi
    -1.44
     artikkelen
    -1.41
     ὑ
    -1.41
     himmel
    -1.41
    ׇ
    -1.39
     miliar
    -1.38
     kveld
    -1.38
     ungefär
    -1.37
    POSITIVE LOGITS
     lutar
    1.43
    那我
    1.36
    了些
    1.33
     stalwart
    1.24
    があり
    1.23
     a
    1.23
     myriad
    1.18
     inept
    1.18
    He
    1.18
     et
    1.18
    Activations Density 0.002%

    No Known Activations