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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8335
    Prev
    Next
    INDEX
    Explanations

    body parts and associated concepts

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

    The neuron activates on mentions of human body parts.

    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
    "]},
    0.66
     }],
    0.60
     السي
    0.57
     }]
    0.57
    nasium
    0.56
    ক্ত
    0.55
     অপ
    0.55
    mph
    0.54
     zarar
    0.54
     Rana
    0.54
    POSITIVE LOGITS
    部的
    0.71
    部の
    0.65
    ద్
    0.65
    椎
    0.64
    CLOSED
    0.63
     breathing
    0.63
    部
    0.63
     muscles
    0.60
    部に
    0.60
     cramps
    0.60
    Activations Density 0.450%

    No Known Activations