© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54284
    Prev
    Next
    INDEX
    Explanations

    flags potential, create, faster speeds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    뱉
    0.43
     changé
    0.40
    ᒎ
    0.39
     variación
    0.39
     thwarted
    0.39
    ሂ
    0.38
     tách
    0.38
    ources
    0.38
     directe
    0.38
    ･･･
    0.38
    POSITIVE LOGITS
     securities
    0.44
     Securities
    0.40
    (
    0.38
     Bernie
    0.38
     Friends
    0.38
    isar
    0.38
    Nr
    0.37
    ({
    0.37
    आय
    0.37
     eighty
    0.36
    Activations Density 0.001%

    No Known Activations