© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25345
    Prev
    Next
    INDEX
    Explanations

    case citations with NY Slip Op

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

    The neuron detects multi‐digit numeric sequences used in legal citations (e.g. case or report numbers, years in brackets).

    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
    ׇ
    -1.29
     to
    -1.17
     ᾿
    -1.11
     "=
    -1.08
     Playoffs
    -1.07
     блюдо
    -1.07
     and
    -1.05
    siasme
    -1.04
     ἡ
    -1.04
    әрмәләр
    -1.04
    POSITIVE LOGITS
     uLocal
    1.27
    ּוֹ
    1.25
    וּ
    1.16
     kabát
    1.12
    Sziasztok
    1.03
    辊
    1.01
     cojín
    1.01
     eccell
    1.00
     trastorno
    1.00
     вони
    0.99
    Activations Density 0.008%

    No Known Activations