© 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. 6463
    Prev
    Next
    INDEX
    Explanations

    liver, stones, fibrosis

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

    The neuron responds to detailed descriptions of medical procedures, tests, and related anatomical or clinical terminology.

    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
    桶
    0.60
    )}_
    0.59
    栃木
    0.59
     wheelchair
    0.58
     Gunung
    0.58
    窑
    0.56
     Kis
    0.56
     بوس
    0.55
    座椅
    0.55
    ♿
    0.55
    POSITIVE LOGITS
     liver
    2.67
     Liver
    2.64
     hepatic
    2.61
     Hepat
    2.59
     hepat
    2.58
    Liver
    2.55
     hepatocytes
    2.52
     hepatocellular
    2.41
    肝
    2.41
     livers
    2.34
    Activations Density 0.372%

    No Known Activations