© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7413
    Prev
    Next
    INDEX
    Explanations

    html attributes and roles

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

    The neuron is triggered by HTML attribute names (e.g. role, presentation, tabindex, dismissable) in code.

    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
     the
    -1.80
     whichever
    -1.52
     a
    -1.45
     anyone
    -1.45
     are
    -1.45
     ANY
    -1.44
     whom
    -1.43
     législation
    -1.43
     any
    -1.41
     up
    -1.40
    POSITIVE LOGITS
     været
    1.85
     لهذه
    1.47
     huevos
    1.46
    م
    1.45
    となっています
    1.45
    هاي
    1.41
    rictive
    1.41
    
    1.40
     داشتن
    1.40
     ſame
    1.39
    Activations Density 0.004%

    No Known Activations