© 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. 79680
    Prev
    Next
    INDEX
    Explanations

    data- attributes, ng- directives, android: attributes

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

    The neuron activates on HTML “data-*” attributes (the “data-” prefix on custom HTML attributes).

    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
     in
    -2.20
     have
    -2.00
     any
    -1.97
     all
    -1.89
    ～！
    -1.80
     that
    -1.73
     because
    -1.73
     from
    -1.70
     may
    -1.70
     (
    -1.69
    POSITIVE LOGITS
    為に
    2.14
    ええ
    1.88
    何回
    1.77
    ことも
    1.73
    ところに
    1.72
    ごめん
    1.68
    すっ
    1.66
     카
    1.64
    凄く
    1.59
    ほら
    1.59
    Activations Density 0.009%

    No Known Activations