© 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. 103847
    Prev
    Next
    INDEX
    Explanations

    diseases and health problems

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

    content related to medical conditions, symptoms, and health problems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     pobre
    -1.05
    ú
    -0.88
    瞟
    -0.81
    лля
    -0.81
     torren
    -0.80
    క్క
    -0.79
    打量
    -0.79
    [:,
    -0.79
    real
    -0.79
    ź
    -0.78
    POSITIVE LOGITS
     diseases
    1.20
     problem
    1.17
     Diseases
    1.13
     lifestyle
    1.04
    Diseases
    1.01
     problems
    1.00
    问题
    0.98
     kemeja
    0.94
    lifestyle
    0.93
     cases
    0.93
    Activations Density 0.028%

    No Known Activations