© 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. 10-GEMMASCOPE-RES-131K
    7. 119716
    Prev
    Next
    INDEX
    Explanations

    occupational injury and illness

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

    words and phrases related to workplace safety, health hazards, and occupational injuries.

    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_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
     more
    -1.27
     sommeil
    -1.13
    tarjeta
    -1.11
     délicieux
    -1.09
     soixante
    -1.08
    noinspection
    -1.08
     Gü
    -1.05
     aberta
    -1.05
     énorme
    -1.05
    جابة
    -1.05
    POSITIVE LOGITS
    这些
    1.39
    那些
    1.29
     mientras
    1.26
     and
    1.25
     χρήση
    1.21
     with
    1.20
    为什么
    1.17
     together
    1.17
                                   
    1.16
     cuando
    1.15
    Activations Density 0.065%

    No Known Activations