© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 654
    Prev
    Next
    INDEX
    Explanations

    python file execution

    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_22_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
    ស្រាយ
    1.05
    patch
    0.91
     বণ্টন
    0.88
    loaders
    0.87
     методи
    0.84
    파일명
    0.84
     공개
    0.84
    [
    0.83
    loading
    0.83
    export
    0.82
    POSITIVE LOGITS
     booking
    1.47
     booked
    1.44
     reservation
    1.33
     visit
    1.25
     visited
    1.25
     Booking
    1.24
     visiting
    1.24
     stayed
    1.22
     recommande
    1.22
     réservation
    1.21
    Activations Density 1.921%

    No Known Activations