© 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. 12153
    Prev
    Next
    INDEX
    Explanations

    racing finish line, start, goal

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

    The neuron strongly activates on the word “finish” (especially in phrases like “finish line”), i.e., it detects mentions of finishing.

    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
     και
    -1.68
    𝒕
    -1.66
     способы
    -1.60
    available
    -1.60
    
    -1.52
    🢒
    -1.52
    塤
    -1.52
    (;;)
    -1.50
     SHOULD
    -1.48
    About
    -1.48
    POSITIVE LOGITS
    嗵
    1.38
     نمی‌
    1.36
     jewe
    1.30
     irrespective
    1.29
    了啊
    1.23
     communicating
    1.23
    胧
    1.23
     españ
    1.20
     кровать
    1.19
     distanci
    1.18
    Activations Density 0.015%

    No Known Activations