© 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. 10-GEMMASCOPE-RES-131K
    7. 118967
    Prev
    Next
    INDEX
    Explanations

    completion event or state

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

    The neuron strongly activates on the word “completed,” especially when it appears in status or process‐completion contexts.

    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
     المكان
    -2.66
     anderen
    -2.61
    ية
    -2.59
     腕
    -2.58
     OTHER
    -2.56
     i
    -2.52
     innymi
    -2.36
    ⩾
    -2.31
     overt
    -2.31
     vielen
    -2.31
    POSITIVE LOGITS
    薆
    3.19
     camiset
    3.09
    尛
    3.00
    汭
    2.89
    話は
    2.89
    鯪
    2.88
     parachoque
    2.86
    赁
    2.77
     火鍋
    2.75
    鸶
    2.70
    Activations Density 0.009%

    No Known Activations