© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11616
    Prev
    Next
    INDEX
    Explanations

    html buttons

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

    This neuron spotlights HTML/XML markup elements—especially attribute names and their values (e.g. class=, rel=, src=, preload=, etc.).

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

    HTML/code attribute syntax, particularly quotes following equals signs in attribute-value pairs.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    HTML markup focused on tag attributes and their quoted values, including DOM code that accesses or modifies those attributes.

    oai_token-act-pair · gpt-5Triggered 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
     ">
    0.65
    !">
    0.65
    काय
    0.61
    ;">
    0.60
    }>
    0.59
     breech
    0.57
    ">
    0.56
     raref
    0.55
    }>{
    0.55
     বেল
    0.55
    POSITIVE LOGITS
     id
    0.84
     Id
    0.68
    id
    0.68
    setAttribute
    0.59
     Idris
    0.59
     ID
    0.57
    τους
    0.55
    atributo
    0.54
    Id
    0.53
    setId
    0.53
    Activations Density 0.004%

    No Known Activations