© 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. 28228
    Prev
    Next
    INDEX
    Explanations

    html table tags

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

    The neuron fires on HTML block‐container tags—especially `<table>` (and to a lesser extent `<div>`) start tags.

    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
    駸
    -1.05
    要去
    -1.05
     its
    -0.96
     πρ
    -0.95
     Souver
    -0.95
     Discussions
    -0.94
    ixante
    -0.94
     to
    -0.92
    並且
    -0.90
    が出来
    -0.90
    POSITIVE LOGITS
    ↵
    1.29
    upuncture
    1.13
     bojo
    1.09
     byl
    1.06
     violin
    1.05
     tedy
    1.05
    .”.
    1.03
    美好
    1.02
     cumbre
    0.99
    **.
    0.98
    Activations Density 0.001%

    No Known Activations