© 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. 129609
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on HTML/XML element names (tags) in code, e.g. tbody, tr, td, table, Path, Group, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    html structure selectors

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     or
    -1.42
     For
    -1.41
     low
    -1.41
     With
    -1.40
     high
    -1.40
     for
    -1.38
     long
    -1.37
    様な
    -1.37
         
    -1.36
     As
    -1.36
    POSITIVE LOGITS
     agres
    1.44
     champignons
    1.41
    峮
    1.40
    edoria
    1.38
     Badan
    1.37
    这让
    1.35
     trabalhadores
    1.33
    AKB
    1.32
     spontan
    1.32
     continuer
    1.32
    Activations Density 0.002%

    No Known Activations