© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103363
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code structures

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

    HTML/XML closing tags and tag-related syntax in markup code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on the ‘<’ characters that begin HTML (or XML) tags, i.e. on the opening delimiters of markup elements.

    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
     concorda
    -1.69
    
    -1.66
     decidiu
    -1.66
     fiscales
    -1.65
     fotógrafo
    -1.62
     poivre
    -1.56
    ⌗
    -1.55
     municipales
    -1.54
     capitán
    -1.52
    なかったので
    -1.52
    POSITIVE LOGITS
    That
    1.84
    chable
    1.80
     wszystkie
    1.75
     "..\..\
    1.74
     они
    1.72
     queste
    1.71
    ür
    1.70
    inning
    1.70
    ;;)
    1.67
    these
    1.66
    Activations Density 0.002%

    No Known Activations