© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 4429
    Prev
    Next
    INDEX
    Explanations

    export default

    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
    Negative Logits
     electrolyte
    0.41
     Chong
    0.40
     wèi
    0.39
     carbides
    0.38
     ここ
    0.37
     spiking
    0.37
     υπάρχ
    0.37
     Returns
    0.36
    偽
    0.35
     heen
    0.35
    POSITIVE LOGITS
    export
    0.45
     export
    0.40
    Woman
    0.40
    exported
    0.39
     Export
    0.38
    arati
    0.38
    rade
    0.37
    typeof
    0.37
    Bar
    0.36
    ()(
    0.36
    Activations Density 0.033%

    No Known Activations