© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1895
    Prev
    Next
    INDEX
    Explanations

    html attribute names and values

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

    This neuron activates on HTML/XML tag attributes (e.g. href, src, title, rel, url).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (‘
    0.75
    kowej
    0.70
     '/',
    0.68
     高級
    0.66
     يست
    0.66
     Wärm
    0.66
     Lobkovic
    0.65
     Hoje
    0.65
     ぐらい
    0.64
     Ahmet
    0.64
    POSITIVE LOGITS
    ="
    1.34
    =""
    1.34
    ="">
    1.18
    =",
    1.17
    ="+
    1.15
    ="#
    1.14
    ="|
    1.14
    ={
    1.13
    ="$
    1.12
    ="{
    1.12
    Activations Density 0.022%

    No Known Activations