© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50968
    Prev
    Next
    INDEX
    Explanations

    plots, math, data, tech

    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
     Agency
    0.39
    وانی
    0.39
    ilane
    0.39
    രക്ഷ
    0.39
    ม
    0.39
     agency
    0.38
     Cre
    0.38
     z
    0.38
     y
    0.38
     administ
    0.37
    POSITIVE LOGITS
    िवी
    0.46
     dàng
    0.44
     сан
    0.44
    userService
    0.43
     ಹೆಸ
    0.43
    erol
    0.42
     ಕೈ
    0.41
     θα
    0.41
    ंधरा
    0.41
     తో
    0.40
    Activations Density 0.002%

    No Known Activations