© 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. 110619
    Prev
    Next
    INDEX
    Explanations

    physical activity and exercise

    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
    ジック
    -0.81
    nship
    -0.78
     zako
    -0.77
    лежки
    -0.77
    leitung
    -0.75
    🎒
    -0.75
    Emo
    -0.74
     Zweig
    -0.73
    emptions
    -0.72
     homme
    -0.71
    POSITIVE LOGITS
     exercise
    4.34
    exercise
    3.17
     Exercise
    2.94
    Exercise
    2.88
     exercising
    2.66
     EXERCISE
    2.38
     exercises
    2.33
     physical
    2.33
    運動
    2.33
     activity
    2.30
    Activations Density 0.079%

    No Known Activations