© 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. 103914
    Prev
    Next
    INDEX
    Explanations

    hospital beds

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

    descriptions of healthcare facilities mentioning bed counts or capacity.

    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
     pasting
    -0.80
     glaubte
    -0.78
    มาณ
    -0.75
    昫
    -0.73
    وش
    -0.70
     Nuggets
    -0.70
     任
    -0.69
    ÁND
    -0.68
     externs
    -0.68
     もう
    -0.68
    POSITIVE LOGITS
     bed
    4.75
     beds
    4.56
     Bed
    3.23
    beds
    3.22
     Beds
    3.22
    bed
    3.17
    Bed
    2.95
    Beds
    2.83
    床
    2.73
     BED
    2.53
    Activations Density 0.033%

    No Known Activations