© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49949
    Prev
    Next
    INDEX
    Explanations

    patients with diseases

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

    This neuron identifies references to patients in medical and clinical contexts, especially when discussing diseases, treatments, or research studies.

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

    find numerical mentions of patient sample sizes in clinical or research contexts.

    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
     menjadikan
    -0.74
    Jav
    -0.73
    illier
    -0.73
     dommage
    -0.73
     dizziness
    -0.72
     llam
    -0.71
     Woj
    -0.70
    Decry
    -0.70
    Woj
    -0.70
    provoking
    -0.69
    POSITIVE LOGITS
     suffering
    3.00
     afflicted
    2.47
     diagnosed
    2.38
    suffering
    1.95
     Suffering
    1.92
     suffers
    1.91
     suffer
    1.91
     affected
    1.90
     مبت
    1.74
     dealing
    1.71
    Activations Density 0.220%

    No Known Activations