© 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. 207827
    Prev
    Next
    INDEX
    Explanations

    rights, collar, We, know, Coming

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

    technical terms and requirements

    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
     Adjustment
    0.49
    煩
    0.48
    son
    0.47
    weise
    0.47
    rat
    0.46
    izio
    0.46
    rius
    0.46
    dds
    0.46
    ct
    0.45
    riage
    0.45
    POSITIVE LOGITS
    ະພັນ
    0.49
     coalesce
    0.46
     гэта
    0.46
     допомогти
    0.46
    ‹
    0.46
     REMOTE
    0.45
    Repository
    0.45
     удовле
    0.45
    >-->
    0.45
     スペ
    0.45
    Activations Density 0.001%

    No Known Activations