© 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. 129968
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on standalone numeric tokens (e.g. page numbers, docket numbers) in legal‐style documents.

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

    legal citation v. respondent appeal

    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
    年から
    -0.91
    кает
    -0.82
    柿
    -0.81
    コネ
    -0.79
    ạnh
    -0.76
     exasper
    -0.75
    siery
    -0.75
    ulia
    -0.75
     ervaring
    -0.74
     aika
    -0.73
    POSITIVE LOGITS
                                   
    0.93
    سک
    0.86
     LICENSE
    0.82
     mismas
    0.75
    rcv
    0.74
     rique
    0.73
    咧
    0.73
    ots
    0.73
    mAuth
    0.73
    setData
    0.72
    Activations Density 0.051%

    No Known Activations