© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64335
    Prev
    Next
    INDEX
    Explanations

    accessing data and attributes

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

    This neuron detects references to HTML data- attributes (e.g. “data-…” in calls like attr("data-access-level")).

    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
    Hé
    -0.75
     Falle
    -0.73
     reception
    -0.71
     Namen
    -0.70
    wag
    -0.70
     Duisburg
    -0.69
    arrow
    -0.69
     Reception
    -0.69
     Luft
    -0.69
    didn
    -0.68
    POSITIVE LOGITS
     data
    1.94
    getAttribute
    1.64
    data
    1.61
    Attr
    1.48
    attr
    1.45
    dataset
    1.30
     attr
    1.21
     Attr
    1.18
     attribute
    1.15
     dataset
    1.13
    Activations Density 0.044%

    No Known Activations