© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61328
    Prev
    Next
    INDEX
    Explanations

    html div tags

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

    The neuron fires on the substring “div” inside HTML angle‐bracket tags—that is, it detects `<div>` or `</div>` elements.

    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
     when
    -1.95
     where
    -1.87
     that
    -1.74
     its
    -1.71
     those
    -1.70
     their
    -1.68
     to
    -1.65
     these
    -1.63
     it
    -1.63
     persönlichen
    -1.63
    POSITIVE LOGITS
     stratég
    1.62
    Ω
    1.50
    llllllll
    1.45
    .
    1.41
     színes
    1.40
    lllllllll
    1.37
     comprennent
    1.37
    irmingham
    1.36
     calendriers
    1.36
     Projek
    1.35
    Activations Density 0.002%

    No Known Activations