© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48816
    Prev
    Next
    INDEX
    Explanations

    pesticide spraying

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

    references to pesticides and agricultural chemicals.

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

    The neuron is detecting mentions of pesticides and related agricultural or environmental chemical agents.

    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
     torque
    -0.78
    cente
    -0.77
    FirebaseAuth
    -0.75
    SEVER
    -0.75
    clat
    -0.74
    錮
    -0.74
     conſ
    -0.73
    PhysRevLett
    -0.73
    remel
    -0.73
    STE
    -0.72
    POSITIVE LOGITS
     spraying
    2.66
     pesticides
    2.58
     pesticide
    2.53
     spray
    2.38
     sprayed
    2.34
     insecticides
    2.16
     herbicides
    2.11
    spray
    2.09
     sprays
    2.09
    Spray
    2.05
    Activations Density 0.070%

    No Known Activations