© 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. 102406
    Prev
    Next
    INDEX
    Explanations

    html div tags with attributes

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

    HTML opening `<div>` tags in code snippets.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on the `<div` tag, i.e. it identifies HTML 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
    vantaged
    -1.68
    1
    -1.66
    $
    -1.60
    uldade
    -1.51
     apsau
    -1.50
     dejando
    -1.49
     but
    -1.48
    なども
    -1.48
    śred
    -1.45
    驁
    -1.45
    POSITIVE LOGITS
     is
    1.84
    opies
    1.77
    t
    1.71
    鼙
    1.70
    inerario
    1.55
     "
    1.53
     these
    1.52
    跸
    1.52
     informé
    1.49
    ěli
    1.48
    Activations Density 0.005%

    No Known Activations