© 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-262K
    7. 137703
    Prev
    Next
    INDEX
    Explanations

    magnetic field

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     cytoplasm
    0.42
     Sint
    0.40
     Delt
    0.39
     Lar
    0.39
     acceler
    0.38
     arbitrarily
    0.38
     Dl
    0.37
     ラ
    0.37
     CASE
    0.37
     equally
    0.36
    POSITIVE LOGITS
     showrooms
    0.42
    ংশে
    0.41
     collapsible
    0.40
     berfungsi
    0.39
     crecer
    0.39
    captive
    0.39
     للخ
    0.39
    ংশ
    0.38
    fänger
    0.38
    ীরের
    0.38
    Activations Density 0.003%

    No Known Activations