© 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. 10-GEMMASCOPE-RES-131K
    7. 12870
    Prev
    Next
    INDEX
    Explanations

    style selectors and css

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

    The neuron fires on code occurrences of the term “style,” e.g. style imports, style‐related file names/extensions, or style classes/attributes in markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    s
    -2.14
    髣
    -1.87
     substantially
    -1.78
    因为他
    -1.74
     Not
    -1.70
    ).
    -1.69
     solely
    -1.66
    粁
    -1.65
     acepción
    -1.64
    篳
    -1.64
    POSITIVE LOGITS
     styles
    1.93
    ⚥
    1.93
     необходимые
    1.91
     имеют
    1.82
     rambut
    1.80
     escalier
    1.78
     inget
    1.73
     Grüße
    1.73
     duros
    1.73
    YOUR
    1.73
    Activations Density 0.028%

    No Known Activations