© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70463
    Prev
    Next
    INDEX
    Explanations

    HTML and XPath selectors

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

    The neuron fires on attribute‐predicate syntax (e.g. “[@…]”, “contains(@id,…)”, CSS/XPath attribute selectors).

    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
     and
    -1.67
    そして
    -1.65
     any
    -1.56
     after
    -1.54
     by
    -1.52
     because
    -1.40
     to
    -1.28
    !(
    -1.28
     before
    -1.28
     during
    -1.27
    POSITIVE LOGITS
    為に
    1.97
    場所で
    1.83
    ところです
    1.73
    のでしょう
    1.70
    あんな
    1.65
    感じが
    1.61
    ところに
    1.60
    のですか
    1.54
    んでしょう
    1.47
    のでしょうか
    1.42
    Activations Density 0.001%

    No Known Activations