© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99711
    Prev
    Next
    INDEX
    Explanations

    html tables

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

    The neuron fires on HTML table row tags (“<tr>”), i.e. it detects the start of a table row.

    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
    <bos>
    -2.36
    我们的
    -2.09
     този
    -2.08
    varlak
    -2.03
    那些
    -2.02
     nuestro
    -1.95
     volontaire
    -1.93
    痢
    -1.91
    หรือ
    -1.88
    畦
    -1.88
    POSITIVE LOGITS
     they
    2.91
    k
    2.73
    s
    2.69
    Ꮑ
    2.63
    am
    2.63
     получил
    2.56
     увидел
    2.45
    
    2.39
    ar
    2.36
    의
    2.36
    Activations Density 0.001%

    No Known Activations