© 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. 39308
    Prev
    Next
    INDEX
    Explanations

    HTML title attributes

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

    The neuron activates on HTML tag attribute names (e.g. title, datetime, tooltip, placement, etc.) whenever they appear in markup.

    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
    kowski
    -1.21
    tubers
    -1.16
     poë
    -1.13
     Contacto
    -1.10
    
    -1.09
     éditions
    -1.08
    pard
    -1.07
     dwóch
    -1.05
     meest
    -1.05
     étudiant
    -1.05
    POSITIVE LOGITS
    This
    1.22
     This
    1.20
     this
    1.16
     indicates
    1.13
     Originally
    1.09
    كد
    1.09
    ちゃんの
    1.05
    当代
    1.05
     despite
    1.05
    There
    1.05
    Activations Density 0.002%

    No Known Activations