© 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. 103553
    Prev
    Next
    INDEX
    Explanations

    html tags

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

    HTML/XML opening angle brackets that mark the start of tags.

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

    The neuron detects HTML/XML tag openings (the “<” and associated tag-name tokens).

    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
    𓋼
    -2.02
     Namun
    -1.98
    chengladbach
    -1.84
    gucig
    -1.83
     vode
    -1.80
     neder
    -1.80
    ଢ
    -1.79
    onekana
    -1.77
    岖
    -1.73
     broder
    -1.73
    POSITIVE LOGITS
    ↵↵
    2.50
    句話
    1.87
    na
    1.77
    t
    1.76
     dotyczą
    1.67
    int
    1.66
     
    1.66
     technically
    1.59
     disturbing
    1.56
    in
    1.55
    Activations Density 0.043%

    No Known Activations