© 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. 65612
    Prev
    Next
    INDEX
    Explanations

    hazardous materials and exposure

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

    hazards, risks, and occupational safety information.

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

    This neuron strongly activates on mentions of “exposure,” especially in the context of occupational or environmental hazard exposure.

    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
    oprecipitation
    -0.87
     imposible
    -0.85
    Enforcement
    -0.84
     dessin
    -0.83
    orios
    -0.81
     siè
    -0.77
    inyin
    -0.77
    URANCE
    -0.75
    Socks
    -0.74
     authentique
    -0.74
    POSITIVE LOGITS
     hazardous
    1.69
     chemicals
    1.60
     dangerous
    1.57
     asbestos
    1.44
     chemical
    1.43
     toxic
    1.37
    hazardous
    1.35
     flammable
    1.33
     radiation
    1.32
     fire
    1.30
    Activations Density 0.053%

    No Known Activations