© 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. 10-GEMMASCOPE-RES-131K
    7. 60894
    Prev
    Next
    INDEX
    Explanations

    food ingredients and descriptions

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

    words and descriptions related to food ingredients, dishes, and culinary terminology.

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

    The neuron strongly activates on specific food items and ingredients (e.g. rice, quinoa, veggies, cashews, coconut, curry) in menu or dish descriptions.

    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
     to
    -1.74
     häufig
    -1.51
    uarga
    -1.50
    рецепт
    -1.49
    orant
    -1.48
    ζει
    -1.42
    おはよう
    -1.40
     Mehrheit
    -1.39
    __':
    -1.38
     său
    -1.37
    POSITIVE LOGITS
     from
    2.11
     with
    1.80
     all
    1.69
     not
    1.66
     more
    1.63
    .
    1.52
     three
    1.45
     as
    1.38
     “
    1.33
     half
    1.29
    Activations Density 0.040%

    No Known Activations