© 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. 41315
    Prev
    Next
    INDEX
    Explanations

    food, taste, and culinary experiences

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

    gastronomic 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
    ม
    0.61
    п
    0.51
     Area
    0.50
    วัด
    0.50
    मी
    0.49
    ร
    0.47
    año
    0.47
    诫
    0.47
     районы
    0.46
    ย
    0.46
    POSITIVE LOGITS
     gastronomic
    0.50
     audiov
    0.49
     gastronomy
    0.49
    phor
    0.49
     memainkan
    0.48
     waiters
    0.47
     foodie
    0.47
     vasomotor
    0.46
     whitish
    0.46
     LANGUAGE
    0.45
    Activations Density 0.000%

    No Known Activations