Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8365
    Prev
    Next
    INDEX
    Explanations

    food, cuisine, and appetite

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

    references to food, cooking, cuisine, and culinary topics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    рым
    -0.71
     パ
    -0.69
    られています
    -0.68
     immunos
    -0.68
    тья
    -0.68
    ěst
    -0.66
     лекар
    -0.66
     breakfast
    -0.66
     כאן
    -0.66
    局面
    -0.65
    POSITIVE LOGITS
     disgust
    0.96
     obo
    0.88
     gastro
    0.85
     Appetite
    0.84
    Foo
    0.82
     Brill
    0.81
     soybeans
    0.79
    ська
    0.78
    дове
    0.78
    ünden
    0.77
    Activations Density 0.032%

    No Known Activations