© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 82669
    Prev
    Next
    INDEX
    Explanations

    business concepts, spaces, and descriptive terms

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

    fortune cookie

    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
     malls
    0.44
     如
    0.44
     最後
    0.44
     可愛
    0.43
     老
    0.42
     就是
    0.42
     když
    0.41
     wheelchairs
    0.41
     totiž
    0.41
     因
    0.41
    POSITIVE LOGITS
    いくつかの
    0.54
    Literatura
    0.47
    ﹑
    0.45
    ுக
    0.45
    according
    0.45
    儚
    0.44
    sning
    0.44
     several
    0.43
     arba
    0.43
    ས
    0.43
    Activations Density 0.001%

    No Known Activations