© 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. 10-GEMMASCOPE-RES-131K
    7. 98647
    Prev
    Next
    INDEX
    Explanations

    end of sentence or legal citation

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

    The neuron activates on numeric citations—especially statute or case references and section numbers (e.g. “19.75,” “30.75,” “(b)(1)”)—i.e. tokens representing legal citation numbers.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     from
    -2.06
     at
    -1.97
     their
    -1.91
     on
    -1.89
     sooooo
    -1.88
     as
    -1.80
     burgeoning
    -1.80
     or
    -1.77
     intensely
    -1.74
     HUGE
    -1.73
    POSITIVE LOGITS
    殽
    2.33
    鶫
    2.11
     verhind
    2.03
    lifies
    2.02
     espere
    1.92
     diverses
    1.86
    −/−
    1.84
     Dinas
    1.84
    actéristi
    1.83
    𐐀
    1.81
    Activations Density 0.002%

    No Known Activations