© 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. 64062
    Prev
    Next
    INDEX
    Explanations

    skeletal muscle

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

    This neuron detects terminology related to skeletal muscle and muscle disorders, particularly focusing on medical terms like "myogenic," "rhabdomyolysis," and "myopathy."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     élégant
    -0.82
    tehende
    -0.79
     acne
    -0.78
    brain
    -0.76
    ﺍ
    -0.75
     intracranial
    -0.75
     españolas
    -0.74
     공
    -0.72
    ە
    -0.72
     headaches
    -0.71
    POSITIVE LOGITS
     muscle
    3.13
    Muscle
    2.70
     Muscle
    2.67
    muscle
    2.63
     muscles
    2.42
     muscular
    2.00
     Muscles
    1.95
    肌肉
    1.77
     Muskel
    1.65
    muscular
    1.63
    Activations Density 0.188%

    No Known Activations