© 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. 34-GEMMASCOPE-RES-131K
    7. 90341
    Prev
    Next
    INDEX
    Explanations

    completion or success

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

    The neuron fires on JavaScript gesture‐ or touch‐event keywords (e.g. “drag,” “swipe,” “hold,” “rotate,” “transform,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    damen
    -0.90
    karten
    -0.89
     aasta
    -0.88
    لمات
    -0.83
    ➗
    -0.82
     पहले
    -0.81
     signifikan
    -0.78
     EXAM
    -0.78
     organisme
    -0.77
     maïs
    -0.77
    POSITIVE LOGITS
     completed
    2.19
     finished
    2.16
     done
    1.95
     finish
    1.87
     complete
    1.82
     success
    1.74
    完成
    1.71
     completion
    1.54
     succeeded
    1.52
     successful
    1.50
    Activations Density 0.052%

    No Known Activations