© 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. 22-GEMMASCOPE-RES-131K
    7. 73170
    Prev
    Next
    INDEX
    Explanations

    data attributes

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

    The neuron fires on occurrences of jQuery data‐attribute usage (e.g. calls to `.data()` or references to `data-*` 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
     siè
    -1.48
     épices
    -1.47
     zwanzig
    -1.45
     faciliter
    -1.40
     lavable
    -1.37
     astonishing
    -1.34
    laa
    -1.30
     luscious
    -1.28
     tohoto
    -1.28
     véhicules
    -1.28
    POSITIVE LOGITS
     at
    1.46
     through
    1.40
     its
    1.39
     had
    1.38
     indicates
    1.36
     serves
    1.34
     provide
    1.32
     or
    1.31
     increase
    1.31
     removes
    1.29
    Activations Density 0.004%

    No Known Activations