© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45736
    Prev
    Next
    INDEX
    Explanations

    css selectors and javascript DOM traversal

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

    The neuron fires on the “>” character when it’s used as a direct‐child combinator (in CSS or jQuery selectors).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    1
    -1.91
     by
    -1.63
     as
    -1.49
     not
    -1.47
    but
    -1.38
     in
    -1.34
     but
    -1.34
     even
    -1.33
    0
    -1.32
     Not
    -1.25
    POSITIVE LOGITS
     capucha
    1.66
     sensaciones
    1.61
     sorpresas
    1.59
    </i>
    1.55
     energías
    1.52
     estampa
    1.52
     cocinas
    1.50
     cuarent
    1.48
     acoged
    1.48
     costumbres
    1.48
    Activations Density 0.019%

    No Known Activations