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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67293
    Prev
    Next
    INDEX
    Explanations

    HTML tables

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

    This neuron fires on occurrences of HTML table tags (the word “table”).

    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
     of
    -2.42
     then
    -2.19
    );
    -1.99
     a
    -1.94
     
    -1.80
        
    -1.79
          
    -1.75
     "
    -1.73
     to
    -1.66
    已是
    -1.64
    POSITIVE LOGITS
     preciosas
    2.05
     hermosas
    2.02
     escuchadas
    1.98
     decoradas
    1.91
     your
    1.88
     tanken
    1.85
    夀
    1.84
    
    1.80
     coloridas
    1.77
     freddo
    1.75
    Activations Density 0.004%

    No Known Activations