© 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. 9981
    Prev
    Next
    INDEX
    Explanations

    restaurants and dining locations

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

    restaurants

    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
    ä
    0.66
     réalisées
    0.60
    д
    0.59
    नर
    0.54
     matériel
    0.54
     narcot
    0.54
     contrace
    0.53
     réalisés
    0.52
    د
    0.52
     enthal
    0.51
    POSITIVE LOGITS
    restaurant
    1.34
     Restaurants
    1.32
    restaurants
    1.27
     Restaurant
    1.27
     restaurant
    1.26
     restaurants
    1.25
    Restaurants
    1.09
    Restaurant
    1.04
     restaurantes
    1.02
     ресторан
    1.02
    Activations Density 0.061%

    No Known Activations