© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7013
    Prev
    Next
    INDEX
    Explanations

    function calls and data structure definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    였습니다
    0.73
     Chill
    0.69
     Esq
    0.68
     Amph
    0.66
    ൂർ
    0.66
    ぇ
    0.66
    ACB
    0.66
     देगा
    0.66
    WAS
    0.65
     Ä
    0.65
    POSITIVE LOGITS
    ()(
    1.56
    ")[
    1.45
    ')[
    1.38
    ()[
    1.26
    "][
    1.24
    ")(
    1.23
    "[
    1.20
    )[
    1.18
    '][
    1.15
    ')(
    1.15
    Activations Density 0.103%

    No Known Activations