© 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. 8028
    Prev
    Next
    INDEX
    Explanations

    bacterial infection

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

    The neuron strongly activates on specialized biomedical and molecular‐biology terminology—long, technical terms like gene or protein names, toxins, operators, concentrations, and other 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
     মানবাধিকার
    0.61
     pund
    0.60
     povos
    0.60
     Cumberland
    0.59
     ayah
    0.59
     BONDS
    0.58
    𝗍
    0.58
    頚
    0.57
    🦌
    0.57
     চেয়ারম্যান
    0.57
    POSITIVE LOGITS
     bacterial
    1.14
     Bacteriol
    1.09
     Bacterial
    1.08
     bacterium
    1.07
     prokary
    1.07
     biofilm
    1.04
     бактери
    1.02
     Bacteria
    1.01
     Escherichia
    1.00
    Bacteria
    1.00
    Activations Density 0.173%

    No Known Activations