© 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. 86947
    Prev
    Next
    INDEX
    Explanations

    insecticides and pest control

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

    technical terminology related to pesticides and insecticides.

    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
    crimson
    -0.81
     Läs
    -0.70
    ：《
    -0.70
    CFU
    -0.69
     británica
    -0.69
     aprecia
    -0.68
    nitz
    -0.66
     terapia
    -0.64
    清洗
    -0.64
     correspond
    -0.63
    POSITIVE LOGITS
     adul
    1.01
     Knock
    0.93
     kills
    0.93
     adulti
    0.92
    Knock
    0.90
    inse
    0.89
     mortality
    0.89
     knockdown
    0.88
     nerve
    0.88
     kill
    0.88
    Activations Density 0.037%

    No Known Activations