© 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. 22-GEMMASCOPE-RES-131K
    7. 130212
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on JavaScript DOM manipulations of CSS—e.g. accessing or setting element.style properties (and related classList/display operations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    CSS properties and values

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     zís
    -1.18
    centerTitle
    -1.16
     веке
    -1.09
    inergic
    -1.07
    "]();
    -1.07
     kogo
    -1.05
    téri
    -1.05
    FILL
    -1.05
     tiefer
    -1.04
     sjuk
    -1.03
    POSITIVE LOGITS
     before
    1.22
     or
    1.18
    ๋า
    1.04
    yalar
    0.98
     crê
    0.94
     Although
    0.94
     strives
    0.94
     aben
    0.93
     genieten
    0.91
     cromo
    0.91
    Activations Density 0.038%

    No Known Activations