© 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. 3151
    Prev
    Next
    INDEX
    Explanations

    hand and fingers

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

    The neuron is highly sensitive to mentions of body parts—especially hands, arms, fingers, elbows, and shoulders.

    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
    ovice
    0.57
     Roof
    0.56
     জরি
    0.55
    itution
    0.55
     スカート
    0.55
    expires
    0.54
    詿
    0.54
     చీ
    0.54
    bron
    0.53
    न्नी
    0.53
    POSITIVE LOGITS
     hands
    2.02
     Hands
    1.98
     hand
    1.95
     fingers
    1.95
    Hands
    1.92
     руки
    1.91
     руку
    1.87
     рука
    1.86
     Hand
    1.85
     손
    1.84
    Activations Density 0.733%

    No Known Activations