© 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. 13579
    Prev
    Next
    INDEX
    Explanations

    nerve, neurons, and excitation

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

    The neuron fires strongly on technical biomedical terms—names of diseases, drugs, physiological processes, and related medical jargon.

    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
    pivot
    0.66
     दुर्गेश
    0.63
    Pivot
    0.63
    मूर्ति
    0.59
     foldable
    0.59
     jaundice
    0.57
     ironing
    0.57
     ढ
    0.56
     adsorbent
    0.55
     creases
    0.55
    POSITIVE LOGITS
     neurons
    1.66
     neuron
    1.54
     nerve
    1.45
     Nerve
    1.40
     neuronal
    1.39
    神经
    1.38
     Neuron
    1.38
    Neurons
    1.38
    neurons
    1.36
     Neur
    1.31
    Activations Density 0.258%

    No Known Activations