© 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. 34-GEMMASCOPE-RES-131K
    7. 77312
    Prev
    Next
    INDEX
    Explanations

    diuretic and furosemide

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

    pharmaceutical drug names, especially diuretics and medications ending in "-tic" or "-ide".

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

    This neuron detects mentions of diuretic drugs (e.g., “diuretic,” “furosemide,” “hydrochlorothiazide”).

    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
     Campaigns
    -0.85
     Fora
    -0.76
     vicissitudes
    -0.76
     Biele
    -0.75
    VIOL
    -0.74
     Retry
    -0.73
     Propag
    -0.73
    ಕ್ಕ
    -0.72
     ナビ
    -0.71
    ródło
    -0.71
    POSITIVE LOGITS
     diure
    1.70
     furo
    1.20
     loop
    1.02
     las
    0.98
     Las
    0.91
     pill
    0.88
     lax
    0.87
     lose
    0.85
     Loop
    0.84
     pee
    0.82
    Activations Density 0.031%

    No Known Activations