© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 1802
    Prev
    Next
    INDEX
    Explanations

    restaurants and eateries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    都道府県
    0.98
     গ্রন্থের
    0.90
    ンダー
    0.89
     Öffentlichkeit
    0.89
     रोगों
    0.88
    에게
    0.87
     ентите
    0.86
    ֗
    0.86
    기를
    0.86
    楫
    0.85
    POSITIVE LOGITS
     restaurant
    2.22
     restaurants
    2.11
     restaurantes
    1.98
     Restaurant
    1.96
     eateries
    1.88
    Restaurant
    1.87
     restoran
    1.84
     eatery
    1.81
     Restaurants
    1.79
     ristorante
    1.78
    Activations Density 0.254%

    No Known Activations