© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92631
    Prev
    Next
    INDEX
    Explanations

    xpath `id` `class` `href` `text` attributes

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

    This neuron detects XPath expressions (e.g. sequences like “//”, predicates with “[…]”, and attribute tests like “@id” or “contains(@…”)

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    hlar
    -1.02
    ppings
    -0.94
    specific
    -0.93
    vét
    -0.91
     endforeach
    -0.88
    usive
    -0.88
    [])
    -0.87
    elements
    -0.83
    лива
    -0.83
    CardModule
    -0.83
    POSITIVE LOGITS
     class
    1.30
    class
    1.23
    id
    1.02
    ような
    0.96
     id
    0.93
     title
    0.84
     role
    0.83
    儘
    0.79
     NG
    0.78
     ・
    0.77
    Activations Density 0.003%

    No Known Activations