© 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. 65949
    Prev
    Next
    INDEX
    Explanations

    fitness classes and training

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

    The neuron activates on mentions of workout venues, equipment, and class or training types (e.g., gym, functional training, spin classes, timetables).

    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
    龛
    -1.59
     vinaigre
    -1.44
     правительства
    -1.43
     Giochi
    -1.23
     السياس
    -1.23
    Ĝ
    -1.19
     financial
    -1.18
    When
    -1.18
     игроков
    -1.16
     раздра
    -1.16
    POSITIVE LOGITS
     ܐ
    1.59
     sessions
    1.54
    🩱
    1.53
     session
    1.44
    ñado
    1.35
     ܝ
    1.34
    FUENTES
    1.33
     الاجتما
    1.31
     الشاشة
    1.29
    🫕
    1.29
    Activations Density 0.025%

    No Known Activations