© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128006
    Prev
    Next
    INDEX
    Explanations

    pesticides and chemical residues

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

    This neuron detects pesticide and insecticide chemical names and compounds, particularly organophosphates, carbamates, and other agricultural chemicals.

    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
     pilares
    -1.52
     was
    -1.45
     conceptos
    -1.38
    метров
    -1.30
    きら
    -1.30
    飒
    -1.30
     diseñadores
    -1.28
    (
    -1.28
     up
    -1.27
     sonidos
    -1.26
    POSITIVE LOGITS
    Maybe
    1.54
    Perhaps
    1.48
    真正
    1.47
    Usually
    1.47
    Always
    1.41
     [''],
    1.36
     verstanden
    1.35
    Really
    1.35
    Still
    1.34
    Again
    1.34
    Activations Density 0.036%

    No Known Activations