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. 31
    Prev
    Next
    INDEX
    Explanations

    food and dining

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    meal
    -1.00
    ed
    -0.99
    up
    -0.94
     Meal
    -0.93
    s
    -0.91
    ellen
    -0.90
    Meal
    -0.89
    ea
    -0.88
    thouse
    -0.86
    nadier
    -0.85
    POSITIVE LOGITS
    service
    1.28
    stuff
    1.13
     intake
    1.03
     processor
    1.02
    🥘
    1.02
     choices
    1.01
     court
    1.01
     preparation
    0.99
    ⿺
    0.98
     poisoning
    0.98
    Activations Density 0.021%

    No Known Activations