© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5542
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on mentions of human body parts and related physiological terms.

    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
     mildew
    0.62
     ionized
    0.61
     bệnh
    0.59
     fertilizer
    0.58
     sickness
    0.56
     विद्य
    0.56
    銹
    0.56
    污水
    0.55
     kleuren
    0.55
     crystals
    0.55
    POSITIVE LOGITS
     abdomen
    1.60
    abdomen
    1.44
    头部
    1.39
     shoulders
    1.38
     ankles
    1.38
     torso
    1.34
    肩膀
    1.33
     wrists
    1.32
     cuello
    1.31
     thighs
    1.30
    Activations Density 1.032%

    No Known Activations