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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38989
    Prev
    Next
    INDEX
    Explanations

    html div tags and attributes

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

    This neuron fires on the “<div” token, i.e. it detects opening HTML div tags.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -1.19
    1
    -1.13
     nowych
    -1.09
     allow
    -1.09
     Erwachsene
    -1.08
    8
    -1.07
     inauguración
    -1.07
    3
    -1.06
    klád
    -1.02
     način
    -1.02
    POSITIVE LOGITS
     prolonged
    1.16
     menthe
    1.12
     actrice
    1.12
     luz
    1.11
    Dtor
    1.09
    ｒ
    1.08
    Économie
    1.07
    烘焙
    1.07
    κτη
    1.07
    एक
    1.07
    Activations Density 0.000%

    No Known Activations