© 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. 10-GEMMASCOPE-RES-131K
    7. 111355
    Prev
    Next
    INDEX
    Explanations

    html attributes

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

    HTML/code attributes like "class", "href", "id", and "target" along with their associated syntax.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on HTML tag attribute names and their associated values (e.g., class=, href=, rel=).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     catalana
    -1.21
     our
    -1.17
     salg
    -1.16
     coreana
    -1.14
     cubana
    -1.14
     vaar
    -1.09
     kado
    -1.05
     fiables
    -1.05
     annen
    -1.03
     tuta
    -1.03
    POSITIVE LOGITS
     chcete
    1.38
    ätt
    1.24
     selain
    1.23
    们的
    1.20
    phism
    1.20
    BOTH
    1.18
     confirmación
    1.18
    sklä
    1.18
     ROCKS
    1.15
    線が
    1.13
    Activations Density 0.025%

    No Known Activations