Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7691
    Prev
    Next
    INDEX
    Explanations

    exercise stress test

    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
    bial
    -0.73
     escritura
    -0.70
    certs
    -0.70
    朗
    -0.69
    plusplus
    -0.68
    smar
    -0.67
    tificate
    -0.66
    🥅
    -0.66
     Sliding
    -0.66
     пля
    -0.66
    POSITIVE LOGITS
     treadmill
    1.20
     exercise
    1.12
     Stress
    1.11
     stress
    1.11
     Exercise
    1.00
    Stress
    0.96
     Tread
    0.95
     Bruce
    0.94
    stress
    0.94
     Exer
    0.90
    Activations Density 0.169%

    No Known Activations