© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2981
    Prev
    Next
    INDEX
    Explanations

    muscle tissue and related physiology

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

    anatomical terms referring to specific muscles and body parts in scientific or medical text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of muscles (especially specific anatomical muscle names and EMG/muscle activity contexts).

    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
    onso
    -0.75
    ɳ
    -0.73
     Roskov
    -0.72
    vacy
    -0.69
     nose
    -0.68
    ítez
    -0.68
    ΕΝ
    -0.68
    TINGS
    -0.67
    raulic
    -0.66
    वेश
    -0.66
    POSITIVE LOGITS
     muscles
    3.84
     muscle
    2.77
     Muscles
    2.38
    muscle
    2.20
    Muscle
    2.13
     мыш
    2.05
     músculos
    2.02
     Muscle
    1.95
    肌肉
    1.80
     mię
    1.65
    Activations Density 0.149%

    No Known Activations