© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15837
    Prev
    Next
    INDEX
    Explanations

    plant sources and their products

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

    This neuron activates for plant-related terms like "sesame," "sunflower," "alfalfa," and other agricultural or botanical references.

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

    The neuron detects mentions of botanical crop names—especially oil‐ or seed‐bearing plants.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    0
    -3.08
    1
    -3.08
    7
    -2.69
    5
    -2.55
    4
    -2.47
    3
    -2.38
    '
    -2.30
    6
    -2.28
    2
    -2.25
    在他
    -2.22
    POSITIVE LOGITS
     multifaceted
    2.48
     When
    2.47
     mischievous
    2.39
     Every
    2.38
    that
    2.33
     gets
    2.30
     people
    2.28
     disconcer
    2.28
     Ironically
    2.25
     facilitates
    2.23
    Activations Density 0.003%

    No Known Activations