© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58280
    Prev
    Next
    INDEX
    Explanations

    css `property: value;`

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

    This neuron detects JavaScript code that assigns to an element’s style property (i.e. “.style.<property> = …”).

    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
    たまに
    -1.38
     with
    -1.36
     for
    -1.35
     from
    -1.34
      
    -1.30
    with
    -1.23
         
    -1.23
    from
    -1.22
    rdb
    -1.20
           
    -1.18
    POSITIVE LOGITS
     imprimi
    1.59
     láser
    1.59
     tanques
    1.58
     why
    1.57
     hidráulica
    1.52
     its
    1.46
     abaste
    1.45
     dzied
    1.43
     neón
    1.42
     colegios
    1.42
    Activations Density 0.007%

    No Known Activations