© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11094
    Prev
    Next
    INDEX
    Explanations

    This neuron detects phrases that explicitly state a condition is not contagious—for example, “cannot catch eczema from coming into contact with someone.”

    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
     tecnologías
    0.59
     প্রার্থনা
    0.59
    ructuring
    0.57
     tecnologie
    0.56
    forderungen
    0.56
    φέρον
    0.55
    📝
    0.55
     времена
    0.54
     賞
    0.54
    ⚪
    0.54
    POSITIVE LOGITS
     infected
    1.97
     Infected
    1.77
     infect
    1.73
    infected
    1.72
     contaminated
    1.71
     infection
    1.60
    contaminated
    1.55
    感染
    1.55
     infecting
    1.53
     संक्रमित
    1.45
    Activations Density 0.296%

    No Known Activations