© 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. 22-GEMMASCOPE-RES-131K
    7. 38510
    Prev
    Next
    INDEX
    Explanations

    class names or elements

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

    The neuron fires on class-related attribute definitions—i.e. it detects occurrences of class or className assignments (the quoted class names) in markup, CSS, or JSX.

    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
    になれば
    -0.98
     himself
    -0.95
     чемпи
    -0.94
     Sold
    -0.92
    riam
    -0.91
     fopen
    -0.91
    unpublished
    -0.90
    /></
    -0.90
    перь
    -0.88
     tolerant
    -0.88
    POSITIVE LOGITS
    éis
    1.05
     abbraccio
    1.03
     géographie
    0.98
    预约
    0.96
    Dí
    0.96
     блюдо
    0.95
     Conseils
    0.93
    izó
    0.93
    ján
    0.93
    και
    0.92
    Activations Density 0.021%

    No Known Activations