© 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. 2059
    Prev
    Next
    INDEX
    Explanations

    The neuron specializes in spotting numeric measurements and statistical values (e.g., lab results, percentages, confidence intervals) in medical or scientific text.

    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
    記入
    0.64
     юби
    0.63
    ตรวจสอบ
    0.63
    idavit
    0.62
     паспо
    0.60
     товары
    0.59
    retrato
    0.58
    alena
    0.57
    DATA
    0.57
    法律
    0.57
    POSITIVE LOGITS
     triglycerides
    0.91
     serum
    0.90
     concentrations
    0.80
     creatinine
    0.78
     triglyceride
    0.75
     proinflammatory
    0.75
     plasma
    0.74
     creatine
    0.73
     cytokines
    0.71
     oxidative
    0.71
    Activations Density 0.106%

    No Known Activations