© 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. 58051
    Prev
    Next
    INDEX
    Explanations

    Div HTML tags and division concepts

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

    This neuron detects mentions of HTML “div” elements (e.g. IDs or tags named “Div”) in code snippets.

    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
    ه
    -3.38
    er
    -2.75
     diğer
    -2.69
     nyel
    -2.55
    哢
    -2.52
     otros
    -2.50
    ной
    -2.47
     společnosti
    -2.44
    e
    -2.42
    erintah
    -2.39
    POSITIVE LOGITS
    埽
    2.81
    其妙
    2.67
     stattfinden
    2.56
    赂
    2.56
    㐂
    2.55
     royaltyfri
    2.47
    and
    2.47
     provocando
    2.45
    劏
    2.44
    ðsíða
    2.41
    Activations Density 0.017%

    No Known Activations