© 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. 22-GEMMASCOPE-RES-131K
    7. 84416
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

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

    The neuron fires strongly on HTML markup tokens—especially the opening `<` plus tag name and attribute tokens (e.g. `<ul class="menu">`, `<li id="notifications_list">`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Faq
    -0.88
     eventually
    -0.87
    JsonHelper
    -0.85
     história
    -0.83
     Bereichen
    -0.82
     soloist
    -0.82
     firebaseConfig
    -0.81
     También
    -0.80
    ESTADO
    -0.80
    óbal
    -0.79
    POSITIVE LOGITS
     αυτά
    0.96
     absol
    0.88
    ALAND
    0.87
    ̋
    0.84
     найти
    0.84
     эти
    0.82
    Book
    0.82
    ReferenceEquals
    0.79
     می‌باشد
    0.78
     eze
    0.77
    Activations Density 0.008%

    No Known Activations