© 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. 10-GEMMASCOPE-RES-131K
    7. 44283
    Prev
    Next
    INDEX
    Explanations

    diuretics or Tyson

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

    medical and pharmaceutical terms, particularly focusing on diuretics and medication names.

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

    The neuron strongly activates on occurrences of the word “diuretics” (often split into “diure” + “tics”) or direct mentions of diuretic drug names.

    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
     
    -3.13
     Since
    -2.77
     Given
    -2.72
     Following
    -2.67
    u
    -2.56
     Although
    -2.55
     Despite
    -2.50
     Initially
    -2.47
     Ideally
    -2.47
     Considering
    -2.45
    POSITIVE LOGITS
    떳
    2.61
     onze
    2.55
    쐈
    2.39
    ⬈
    2.38
    ]</
    2.38
    
    2.34
     แปล
    2.31
     baumwolle
    2.31
     karier
    2.30
     अच्छा
    2.30
    Activations Density 0.008%

    No Known Activations