© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8482
    Prev
    Next
    INDEX
    Explanations

    exchange rates

    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
    ゴム
    1.01
    рабо
    0.98
     ски
    0.96
    at
    0.95
    扒
    0.94
    of
    0.93
    kota
    0.93
     jog
    0.93
     script
    0.92
    more
    0.92
    POSITIVE LOGITS
     আপন
    1.39
     veamos
    1.39
    <unused1938>
    1.37
    ડા
    1.36
     upside
    1.36
    沧
    1.35
    ശ്ച
    1.32
     soundness
    1.31
    ന്ദ
    1.30
     erythrocytes
    1.30
    Activations Density 0.001%

    No Known Activations