© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9544
    Prev
    Next
    INDEX
    Explanations

    Guatemala, Belize, Maya, Oscar Romero, Lua

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

    Lua code and locations

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     театра
    0.42
     kho
    0.41
    驪
    0.40
     পাকিস্তানকে
    0.40
     zasad
    0.39
     япон
    0.39
    飨
    0.39
    ͘
    0.38
    aksha
    0.38
     नाभ
    0.38
    POSITIVE LOGITS
     Guatemala
    1.57
     Guatem
    1.51
     Mayan
    1.27
     Belize
    1.23
     Lua
    1.20
     Maya
    1.17
     Nicar
    1.14
     lua
    1.11
     Nicaragua
    1.10
     maya
    1.10
    Activations Density 0.073%

    No Known Activations