© 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. 5554
    Prev
    Next
    INDEX
    Explanations

    HTML attributes like `data-`

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

    The neuron is strongly activated by HTML/XML tag names and attribute names (e.g. “href,” “namespace,” “prefix,” “charset,” “width,” etc.).

    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
     '>
    0.61
     myWeb
    0.61
     %>
    0.61
     ?>
    0.60
     ఆయన
    0.58
    }_
    0.57
    ->_
    0.56
    ']>;
    0.55
     веб
    0.54
     adlı
    0.54
    POSITIVE LOGITS
    ="
    1.45
    =\"
    1.22
    ="\
    1.19
    =\""
    1.17
    =”
    1.13
    ="$
    1.10
    =""
    1.08
    ="'
    1.07
    ="-
    1.06
     "=
    1.05
    Activations Density 0.023%

    No Known Activations