© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56783
    Prev
    Next
    INDEX
    Explanations

    fitness and exercise activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     D
    0.44
     G
    0.42
     Helicopter
    0.42
    outline
    0.39
     בה
    0.38
    heur
    0.37
     Goat
    0.37
    moto
    0.37
     translate
    0.37
    地
    0.37
    POSITIVE LOGITS
     gym
    0.75
     gyms
    0.74
     workout
    0.72
     Fitness
    0.70
    Fitness
    0.69
    健身
    0.69
     Workout
    0.68
     fitness
    0.65
     Gym
    0.63
    Gym
    0.63
    Activations Density 0.092%

    No Known Activations