© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118848
    Prev
    Next
    INDEX
    Explanations

    fitness industry figures and gyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    驾驶
    -0.95
    žiu
    -0.81
    ulatum
    -0.75
     palliative
    -0.75
    тору
    -0.75
     Minecraft
    -0.74
    taxi
    -0.74
     agricultural
    -0.74
    OCOL
    -0.73
    плом
    -0.73
    POSITIVE LOGITS
     fitness
    3.38
     workout
    3.06
     gym
    2.84
    fitness
    2.83
     Fitness
    2.66
     workouts
    2.63
    Fitness
    2.63
     gyms
    2.36
     exercise
    2.34
     Workout
    2.25
    Activations Density 0.127%

    No Known Activations