© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66407
    Prev
    Next
    INDEX
    Explanations

    decide the winner

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

    This neuron detects words and phrases that signal the act of deciding or determining an outcome—e.g. deciding a winner, crowning a champion, or determining who rules.

    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
     to
    -1.60
     возможно
    -1.47
    leroi
    -1.39
    нусы
    -1.38
    还不错
    -1.35
    ;
    
    -1.35
    ];
    -1.33
    ijnt
    -1.33
     \\
    -1.30
    tison
    -1.30
    POSITIVE LOGITS
     a
    2.39
     this
    1.74
     where
    1.49
     whether
    1.48
     szükség
    1.35
     when
    1.34
     funguje
    1.32
     decide
    1.30
     églises
    1.29
     potře
    1.27
    Activations Density 0.048%

    No Known Activations