© 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. 38523
    Prev
    Next
    INDEX
    Explanations

    side effects

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

    phrases related to "side effects" in medical or pharmaceutical contexts.

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

    the neuron detects mentions of treatment adverse effects, especially the phrase “side effects.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     this
    -1.70
     [
    -1.66
     Everyone
    -1.64
     但
    -1.55
     You
    -1.55
     During
    -1.51
     through
    -1.48
    "
    -1.48
     有
    -1.43
    Ｃ
    -1.43
    POSITIVE LOGITS
     místa
    1.76
     envíos
    1.73
     těchto
    1.70
     новым
    1.69
     vetores
    1.66
     sám
    1.64
     nových
    1.62
     botões
    1.59
     giras
    1.57
     nieuwe
    1.55
    Activations Density 0.036%

    No Known Activations