© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 118755
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and specific phrases like "The present invention"

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

    HTML and XML code, particularly angle brackets, tags, class/id attributes, and structural markup elements.

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

    This neuron specializes in detecting HTML tag attributes (especially class and id declarations) within markup.

    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
     will
    -1.51
    Locatie
    -1.32
    pentru
    -1.32
     ktorí
    -1.31
     Instead
    -1.30
    是一個
    -1.29
     olacaktır
    -1.29
    场比赛
    -1.27
     jemals
    -1.27
    strnc
    -1.27
    POSITIVE LOGITS
     with
    1.38
    СКИ
    1.21
     another
    1.18
     of
    1.15
    if
    1.11
    Men
    1.11
     itself
    1.10
     medži
    1.10
     ComboBox
    1.09
    another
    1.08
    Activations Density 0.012%

    No Known Activations