© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98291
    Prev
    Next
    INDEX
    Explanations

    ON APPEAL

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

    The neuron consistently activates on numeric sequences—particularly court docket or citation numbers—often appearing right after a parenthesis.

    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
    ICOLON
    -0.91
     Aguas
    -0.88
    acă
    -0.78
    Geral
    -0.78
    Слайд
    -0.77
     могли
    -0.77
     term
    -0.77
     AssemblyCulture
    -0.76
    طل
    -0.75
     ajuta
    -0.75
    POSITIVE LOGITS
    xxi
    0.95
    ఢ
    0.88
    cámara
    0.85
     ہیں۔
    0.82
    افی
    0.82
     рекомендации
    0.82
    ITHER
    0.81
    ឱ
    0.81
    <>
    0.81
    anganronpa
    0.80
    Activations Density 0.036%

    No Known Activations