© 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. 31-GEMMASCOPE-2-RES-262K
    7. 28079
    Prev
    Next
    INDEX
    Explanations

    South Africa politics and geography

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

    South Africa

    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
    Not in Any Lists

    No Comments

    Negative Logits
     المعادله
    0.44
     ܒ
    0.44
    )\$(
    0.44
     봄
    0.43
    >..\
    0.43
     tenement
    0.42
     tiu
    0.42
    賖
    0.42
     tenements
    0.41
     floppy
    0.41
    POSITIVE LOGITS
    🇿
    0.83
     Johannesburg
    0.77
     Zuma
    0.73
     Durban
    0.71
    Zulu
    0.69
     Pretoria
    0.67
     Gauteng
    0.67
     Zulu
    0.66
     KwaZulu
    0.66
     ANC
    0.63
    Activations Density 0.024%

    No Known Activations