© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128540
    Prev
    Next
    INDEX
    Explanations

    swine diseases and industry

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

    references to swine, pigs, and associated animal diseases like H1N1 and other viruses.

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

    The neuron activates on mentions of “swine” (or pig) and swine-associated influenza or other pig-specific pathogens/terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    2
    -3.17
    ’
    -2.98
    1
    -2.67
    '
    -2.66
    3
    -2.53
    “
    -2.50
    0
    -2.47
    5
    -2.30
    es
    -2.27
    ar
    -2.25
    POSITIVE LOGITS
    OUTUBE
    2.45
     pintadas
    2.34
    Технические
    2.13
    賔
    2.09
    Плюсы
    2.09
    ização
    2.08
    ญี่ป
    2.08
     decoradas
    2.05
     blancas
    2.02
     systé
    2.02
    Activations Density 0.009%

    No Known Activations