© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8869
    Prev
    Next
    INDEX
    Explanations

    holding actions

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

    This neuron detects mentions of body parts (especially limbs like arms, hands, elbows, and related anatomy) in exercise instruction contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الملابس
    1.09
     옷
    1.02
     roupas
    0.98
     clothing
    0.98
     clothes
    0.96
    Clothing
    0.93
     jeans
    0.90
     Clothing
    0.88
     pakaian
    0.86
     لباس
    0.86
    POSITIVE LOGITS
    持
    0.84
     held
    0.83
    held
    0.80
    Holding
    0.74
    肩
    0.73
    を持ち
    0.72
     holding
    0.71
    抱
    0.71
     HOLD
    0.69
    holding
    0.68
    Activations Density 0.344%

    No Known Activations