© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83658
    Prev
    Next
    INDEX
    Explanations

    YMCA, gym, fitness

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

    gyms and personal fitness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glioma
    0.44
    맑
    0.41
    蓖
    0.40
     sólido
    0.40
    悎
    0.39
    zości
    0.39
     অভিনয়ের
    0.39
    🌶
    0.39
    jeća
    0.38
     Ordn
    0.38
    POSITIVE LOGITS
     gyms
    0.74
     gym
    0.72
     YMCA
    0.64
     Gym
    0.63
     gymnasium
    0.59
    Gym
    0.59
    Fitness
    0.57
    健身
    0.55
     fitness
    0.55
     Fitness
    0.55
    Activations Density 0.141%

    No Known Activations