© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66095
    Prev
    Next
    INDEX
    Explanations

    women's leagues and tournaments

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

    This neuron detects terms and tokens associated with women’s sports contexts, especially mentions of “Women’s” (and related league/tournament names) in player and competition descriptions.

    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
    卫生间
    -1.35
    </h3>
    -1.32
    </h4>
    -1.13
    着一个
    -1.13
    赝
    -1.13
    ました
    -1.08
     refrigerador
    -1.07
     ,
    
    -1.05
    ək
    -1.03
    着一
    -1.02
    POSITIVE LOGITS
    玊
    1.15
    ünst
    1.13
     ダイヤ
    1.13
     presence
    1.11
     only
    1.09
     you
    1.08
    opaque
    1.07
     needed
    1.05
    éric
    1.05
     herself
    1.04
    Activations Density 0.047%

    No Known Activations