© 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. 104636
    Prev
    Next
    INDEX
    Explanations

    legal citations following numbers

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

    The neuron fires on standalone numeric tokens (sequences of digits), such as error-code numbers, timestamps, line numbers, or legal citation volume and page numbers.

    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
     niečo
    -1.03
     Forsch
    -0.93
    に入れ
    -0.91
    ров
    -0.88
    <mask>
    -0.88
    の方に
    -0.88
     bodies
    -0.87
     languid
    -0.87
     something
    -0.86
    で作
    -0.85
    POSITIVE LOGITS
    と思ったら
    1.09
    Более
    1.01
    互動
    1.01
    获得了
    0.97
    年は
    0.91
     tillbaka
    0.91
    Глава
    0.91
    Ещё
    0.88
     dorada
    0.88
    Один
    0.88
    Activations Density 0.003%

    No Known Activations