© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13869
    Prev
    Next
    INDEX
    Explanations

    technical audit, prayer dress, cultural exchange

    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
    に関する
    1.74
     terbaru
    1.52
    についての
    1.51
    有哪些
    1.50
    ®
    1.49
    ™
    1.49
    による
    1.47
    における
    1.47
    について
    1.47
    [*][[
    1.46
    POSITIVE LOGITS
     sogenannten
    1.37
     Hälfte
    1.30
    전히
    1.20
    zetac
    1.19
     kuid
    1.17
     beiden
    1.14
     möglichst
    1.14
    slightly
    1.14
    xsd
    1.13
     obe
    1.11
    Activations Density 0.071%

    No Known Activations