© 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. 10-GEMMASCOPE-RES-131K
    7. 20908
    Prev
    Next
    INDEX
    Explanations

    USTC citations

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

    This neuron activates on official reporter citations—volume and reporter abbreviations (e.g. “Ed.”, “Wall.”, “U.S.”) in legal case references.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     like
    -2.00
     since
    -1.99
     in
    -1.93
     as
    -1.84
     who
    -1.77
     with
    -1.76
     and
    -1.74
     if
    -1.59
     first
    -1.52
     because
    -1.48
    POSITIVE LOGITS
    儇
    1.80
    replyreport
    1.77
    licopter
    1.75
     énorme
    1.66
    킁
    1.61
     éte
    1.59
    茀
    1.59
     améli
    1.59
    potranspiration
    1.59
    ər
    1.56
    Activations Density 0.001%

    No Known Activations