© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34376
    Prev
    Next
    INDEX
    Explanations

    rivalry

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

    The neuron detects terms related to rivalry, competition, or oppositional matchups.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    なぎ
    -0.94
    ậy
    -0.88
     frescas
    -0.83
    オール
    -0.81
     Schweizer
    -0.80
    addComponent
    -0.80
    TODOS
    -0.79
    ブン
    -0.78
     distor
    -0.77
     Peripheral
    -0.77
    POSITIVE LOGITS
     rival
    2.19
     rivalry
    1.90
    rival
    1.79
     rivals
    1.70
     competitor
    1.51
     competitors
    1.46
    competi
    1.38
    Rival
    1.34
     Rival
    1.30
     competing
    1.21
    Activations Density 0.071%

    No Known Activations