© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8243
    Prev
    Next
    INDEX
    Explanations

    If you would like to explore

    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
     आपण
    0.91
    VIDED
    0.90
     Utilisez
    0.88
     necessariamente
    0.88
     arada
    0.88
     நீங்கள்
    0.88
     berarti
    0.88
     _:
    0.87
     podremos
    0.85
     PLEASE
    0.85
    POSITIVE LOGITS
    <sup>
    3.27
    [
    2.98
     [
    2.86
    ,[
    2.45
     [[
    2.31
    .[
    2.27
     ([
    2.26
     $[
    2.23
     ${
    2.20
    [[
    2.04
    Activations Density 0.422%

    No Known Activations