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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108460
    Prev
    Next
    INDEX
    Explanations

    yoga happens elsewhere

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is triggered by mentions of yoga practice—especially the word “yoga” and the names of specific yoga poses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Sociedad
    -0.91
    constexpr
    -0.88
     gevallen
    -0.88
    JECTION
    -0.81
    Computing
    -0.81
    zen
    -0.80
     обеспечить
    -0.80
    داری
    -0.79
    wendungen
    -0.79
    рги
    -0.79
    POSITIVE LOGITS
     practice
    1.05
     teacher
    1.03
     sequences
    1.00
     sequence
    0.99
     exploration
    0.93
     students
    0.91
     teachers
    0.91
     juicy
    0.86
     maschile
    0.85
     explorations
    0.84
    Activations Density 0.017%

    No Known Activations