© 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. 101407
    Prev
    Next
    INDEX
    Explanations

    plant diseases and symptoms

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

    names of plant diseases and pathogens in scientific literature.

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

    The neuron activates on mentions of plant disease or pathogen names (e.g., anthracnose, coffee leaf rust, bacterial blight).

    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
     território
    -1.48
     a
    -1.38
    usitis
    -1.35
     anúncio
    -1.33
    olda
    -1.33
    それにしても
    -1.30
    enablog
    -1.27
     seçenek
    -1.27
     deputado
    -1.26
    üenza
    -1.25
    POSITIVE LOGITS
     first
    1.28
     two
    1.27
     ними
    1.27
     when
    1.23
     εύ
    1.23
     like
    1.20
    illoin
    1.19
     winter
    1.18
     second
    1.17
     take
    1.14
    Activations Density 0.079%

    No Known Activations