© 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. 102672
    Prev
    Next
    INDEX
    Explanations

    products and health topics

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

    content related to tobacco products, smoking, and vaping.

    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
    attamento
    -0.82
    闌
    -0.78
     Freezing
    -0.78
    置信
    -0.77
     Deviation
    -0.77
     Climatic
    -0.77
     climatic
    -0.76
    resetPassword
    -0.76
     zs
    -0.75
    Shard
    -0.75
    POSITIVE LOGITS
     youth
    1.19
     product
    1.12
     aerosol
    1.05
     vaping
    1.04
     FDA
    1.00
     TikTok
    0.99
     device
    0.99
    EVAL
    0.97
     Youth
    0.96
     Product
    0.96
    Activations Density 0.017%

    No Known Activations