© 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. 10-GEMMASCOPE-RES-131K
    7. 100920
    Prev
    Next
    INDEX
    Explanations

    pesticides and their application

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

    words related to pesticides and agricultural chemicals.

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

    The neuron is tuned to detect mentions of pesticides and related agrochemical terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    as
    -3.16
    (
    -2.81
    I
    -2.67
    us
    -2.66
     ‘
    -2.59
    [
    -2.53
    \
    -2.52
    In
    -2.42
    »
    -2.39
    h
    -2.38
    POSITIVE LOGITS
     短发
    2.52
    ⃨
    2.52
    뻣
    2.52
     takimi
    2.47
     szczeg
    2.47
    🫴
    2.45
    ⡂
    2.36
    März
    2.33
     häufigsten
    2.27
    slika
    2.25
    Activations Density 0.003%

    No Known Activations