© 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. 9476
    Prev
    Next
    INDEX
    Explanations

    HTML tables

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

    The neuron detects HTML table structure elements (e.g. the opening <table>, <tbody>, and <tr> 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
     to
    -1.42
    และ
    -1.06
    loggen
    -1.05
     any
    -1.02
     hunde
    -1.02
     ingat
    -1.00
     that
    -1.00
    return
    -0.99
     kuiten
    -0.97
     performances
    -0.96
    POSITIVE LOGITS
     срав
    1.17
     unaweza
    1.13
     они
    1.12
     ambayo
    1.09
     utaf
    1.06
     ambao
    1.05
     habari
    1.03
     They
    1.03
     probablemente
    1.02
     зачем
    1.00
    Activations Density 0.007%

    No Known Activations