© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123817
    Prev
    Next
    INDEX
    Explanations

    Russia, tortoise, Solomon

    np_acts-logits-general · gemini-2.5-flash-lite

    corrections, spelling improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     do
    0.43
    馴
    0.42
    n
    0.41
     mince
    0.40
     reiter
    0.39
    اا
    0.39
     Sod
    0.39
     T
    0.39
    否定
    0.39
     toler
    0.38
    POSITIVE LOGITS
    ক্ষে
    0.49
     converg
    0.49
     моз
    0.48
     przedsi
    0.48
     कोशिकाओं
    0.46
     পশ্চিমবঙ্গে
    0.46
    ।.
    0.45
     शंक
    0.45
     membrana
    0.45
     lmao
    0.45
    Activations Density 0.000%

    No Known Activations