© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68445
    Prev
    Next
    INDEX
    Explanations

    illness and discomfort

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

    words and phrases related to illness, infection, and fever.

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

    The neuron responds to metaphorical illness or contagion terms—words like “fever,” “itch,” “bug,” and “infectious” used to describe strong urges or afflictions.

    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
    </u>
    -1.70
     bicicletas
    -1.56
     story
    -1.45
    </em>
    -1.42
     llantas
    -1.39
    (
    -1.33
    crania
    -1.32
    _
    -1.32
     câteva
    -1.30
     streamlined
    -1.30
    POSITIVE LOGITS
     TERR
    1.45
     manières
    1.42
     =-\
    1.38
    Spolja
    1.38
     herencia
    1.36
     diğer
    1.34
    %");
    1.34
    asInstanceOf
    1.32
    isbol
    1.32
    bleshooting
    1.32
    Activations Density 0.035%

    No Known Activations