© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115806
    Prev
    Next
    INDEX
    Explanations

    infectious diseases

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

    terms related to infectious diseases in medical and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects mentions of “infectious” (and related infection/disease) terminology in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aties
    -0.90
     vod
    -0.87
    cially
    -0.86
     augus
    -0.85
    燥
    -0.84
     medis
    -0.82
    冰
    -0.82
     realm
    -0.82
    ES
    -0.82
    mento
    -0.81
    POSITIVE LOGITS
     diseases
    1.09
    IOUS
    1.02
     Diseases
    0.90
     dotyczące
    0.89
     spreading
    0.88
     cláus
    0.86
     disease
    0.86
    údio
    0.85
    OUS
    0.84
    gint
    0.84
    Activations Density 0.034%

    No Known Activations