© 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. 10-GEMMASCOPE-RES-131K
    7. 87244
    Prev
    Next
    INDEX
    Explanations

    html attributes

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

    The neuron fires on bits of markup/ code—particularly attribute tokens (like numeric values, style/CSS declarations, and HTML tag/attribute snippets).

    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
    Гри
    -2.03
    ของ
    -1.98
    Гео
    -1.79
    Mereka
    -1.73
    Pemer
    -1.72
    Зе
    -1.70
    Siapa
    -1.70
    чера
    -1.68
    Сти
    -1.67
    Kenapa
    -1.66
    POSITIVE LOGITS
         
    2.17
           
    2.13
               
    2.08
    <h2>
    2.02
            
    1.98
     on
    1.98
                 
    1.98
        
    1.94
    <blockquote>
    1.91
              
    1.90
    Activations Density 0.035%

    No Known Activations