© 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. 93955
    Prev
    Next
    INDEX
    Explanations

    lettuce and celery

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

    words related to plants and vegetables, particularly lettuce, celery, and iceberg.

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

    The neuron strongly activates on mentions of leafy salad vegetables (e.g., lettuce, iceberg, celery, cabbage).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Agarwal
    -0.78
     Jha
    -0.74
     Kae
    -0.71
     Woodruff
    -0.71
    Finland
    -0.71
    strongly
    -0.70
     AssertionError
    -0.69
    llas
    -0.69
    Sweden
    -0.69
    лам
    -0.68
    POSITIVE LOGITS
     lettuce
    1.57
     iceberg
    1.23
     Lettuce
    1.11
    🥬
    1.01
     celery
    1.00
     romaine
    0.91
    runchy
    0.84
     crunchy
    0.79
    Lettuce
    0.77
     wraps
    0.73
    Activations Density 0.027%

    No Known Activations