© 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. 22-GEMMASCOPE-RES-131K
    7. 32712
    Prev
    Next
    INDEX
    Explanations

    html script and style tags

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

    The neuron activates on HTML `<script>` tags (i.e. the start and end of embedded script blocks).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sensual
    -1.13
     newOwner
    -1.07
    Beschrijving
    -0.98
    しまいます
    -0.98
     recognizable
    -0.96
     kohdetta
    -0.94
    erweise
    -0.93
     découvre
    -0.93
    曲目
    -0.92
    吉他
    -0.91
    POSITIVE LOGITS
    bė
    1.20
     both
    1.11
     футболка
    0.99
    唆
    0.95
    fancybox
    0.92
    BOTH
    0.91
     σήμερα
    0.91
     promote
    0.90
     respectively
    0.88
    mountable
    0.88
    Activations Density 0.001%

    No Known Activations