© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8106
    Prev
    Next
    INDEX
    Explanations

    Southeast Asia countries

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scranton
    0.51
     Railroad
    0.48
    鳟
    0.46
     Haskell
    0.46
    轵
    0.46
    ⟋
    0.46
     Raster
    0.46
     Trout
    0.44
    璺
    0.44
    astră
    0.43
    POSITIVE LOGITS
     Singapore
    1.77
    Singapore
    1.74
     singapore
    1.47
     सिंगापुर
    1.45
    新加坡
    1.43
     Singapura
    1.32
     Malaysian
    1.13
     Malaysia
    1.12
     Malays
    1.09
     Brunei
    1.04
    Activations Density 0.100%

    No Known Activations