© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20773
    Prev
    Next
    INDEX
    Explanations

    nonsteroidal anti-inflammatory drugs

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

    pharmaceutical and anti-inflammatory drug names (like NSAID, diclofenac, indomethacin).

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

    The neuron fires on mentions of non‐steroidal anti‐inflammatory drugs—both the acronym “NSAID/NSAIDs” and specific drug names (e.g., diclofenac, naproxen, ibuprofen).

    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
    diseases
    -1.74
     土産
    -1.64
    creens
    -1.59
     importantly
    -1.54
     Comprometido
    -1.51
     撮り
    -1.50
     vivent
    -1.48
     telas
    -1.48
    setLayoutManager
    -1.48
    bullets
    -1.48
    POSITIVE LOGITS
    2
    2.05
    e
    1.81
    b
    1.73
     our
    1.63
    if
    1.62
    q
    1.61
    i
    1.59
    ts
    1.54
    f
    1.52
    1.44
    Activations Density 0.037%
    No Known Activations