© 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. 22-GEMMASCOPE-RES-131K
    7. 36308
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code structure

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

    This neuron detects markup tag names (e.g. div, view, text, p) in HTML/XML/code templates.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.10
    ,
    -1.01
     for
    -0.94
     begged
    -0.93
    8
    -0.90
    else
    -0.89
    دهی
    -0.88
     任
    -0.87
    밖
    -0.85
    9
    -0.84
    POSITIVE LOGITS
     ajusta
    1.22
     delgada
    1.17
    chemise
    1.13
     jednocześnie
    1.10
     your
    1.07
     hacían
    1.07
     נוספת
    1.05
     preparado
    1.02
     its
    1.02
    dryer
    1.01
    Activations Density 0.006%

    No Known Activations