© 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
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2225
    Prev
    Next
    INDEX
    Explanations

    cooking, chefs, and recipes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fiber
    0.78
    🐫
    0.76
     fibre
    0.72
    礦
    0.71
    emetery
    0.69
     fibers
    0.69
     खनिज
    0.68
     tubercle
    0.68
    矿
    0.68
     vertebral
    0.66
    POSITIVE LOGITS
     cooking
    4.40
     cooks
    4.23
     cook
    4.16
     Cooking
    4.15
     chefs
    4.12
    Cooking
    4.09
    cooking
    3.99
     chef
    3.98
     Chef
    3.86
     Chefs
    3.76
    Activations Density 1.389%

    No Known Activations