© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52214
    Prev
    Next
    INDEX
    Explanations

    culinary chefs and connected kitchen partners

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

    cooking and culinary terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     कैलाश
    0.41
    发电
    0.41
     NSTX
    0.40
     scrot
    0.40
    틋
    0.40
    dSample
    0.39
    忿
    0.39
     하나님의
    0.39
    ⩾
    0.39
     ""}
    0.39
    POSITIVE LOGITS
     culinary
    1.16
     chefs
    1.07
     Cooking
    1.07
     cookbooks
    1.05
     Culinary
    1.05
     cooking
    1.03
     chef
    1.02
     cookbook
    1.01
     cooks
    1.00
     kitchen
    1.00
    Activations Density 0.143%

    No Known Activations