© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63322
    Prev
    Next
    INDEX
    Explanations

    influenza, cough, throat, antiviral

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

    scientific terms related to influenza viruses and their treatments.

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

    The neuron strongly activates on mentions of the antiviral drug oseltamivir (and closely associated influenza 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_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
     Tox
    -0.82
     Insulin
    -0.79
    𝕀
    -0.78
    Token
    -0.76
    الف
    -0.75
     Tokens
    -0.75
     ovarian
    -0.75
     pion
    -0.75
     Lash
    -0.75
     Token
    -0.74
    POSITIVE LOGITS
     throat
    1.20
     honey
    1.18
     cough
    1.13
     Cough
    1.05
     Honey
    1.05
     Throat
    1.02
    honey
    1.01
     influenza
    0.97
    Cough
    0.97
    喉
    0.95
    Activations Density 0.036%

    No Known Activations