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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55876
    Prev
    Next
    INDEX
    Explanations

    yoga and related practices

    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
     orbital
    -0.81
     voter
    -0.80
     Erziehung
    -0.79
    ▢
    -0.78
    gnu
    -0.77
    holo
    -0.77
    ื่อง
    -0.75
    JEL
    -0.75
     shaving
    -0.74
     бого
    -0.74
    POSITIVE LOGITS
     yoga
    2.92
     Yoga
    2.44
     yog
    2.31
    Yoga
    2.23
    yoga
    1.99
     practice
    1.95
     Yog
    1.89
     йо
    1.71
     practicing
    1.65
    yog
    1.64
    Activations Density 0.043%

    No Known Activations