© 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. 19816
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and values

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

    This neuron detects numeric values assigned to HTML (or XML) tag attributes (e.g., width="…", style="width:…", xmlns="…").

    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
    ,”
    -2.17
    ’
    -2.11
    !”
    -2.00
     what
    -1.84
     (‘
    -1.77
     (“
    -1.70
    鋮
    -1.66
     riveting
    -1.62
     Before
    -1.59
     bolster
    -1.59
    POSITIVE LOGITS
    dicional
    1.89
    
    1.81
    馓
    1.81
    "'
    1.76
    </em>
    1.75
    
    1.74
    ⩕
    1.73
    偸
    1.73
     "
    1.71
     musíte
    1.71
    Activations Density 0.010%

    No Known Activations