© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10349
    Prev
    Next
    INDEX
    Explanations

    restaurants, cafes, hotels, and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     AGRICULTURE
    1.05
     deposited
    1.03
    体操
    1.01
     pect
    1.01
     pem
    1.00
     py
    1.00
    AGRIC
    0.98
    尿
    0.98
    ophosph
    0.97
     Mathematica
    0.97
    POSITIVE LOGITS
     ร้าน
    2.26
    店内
    2.20
    ร้าน
    2.20
    店铺
    2.11
    店家
    2.09
     restaurant
    2.08
    お店
    2.07
    店
    2.03
     pizzeria
    2.02
     Restaurant
    2.00
    Activations Density 0.587%

    No Known Activations