© 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. 40-GEMMASCOPE-2-RES-65K
    7. 49071
    Prev
    Next
    INDEX
    Explanations

    Latin America and South America regions

    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_40_width_65k_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
     €
    0.45
    ⁶
    0.42
     ಬಿಜೆ
    0.41
     dů
    0.41
    Ped
    0.39
     rues
    0.39
     Kerala
    0.38
     ²
    0.38
    पंजाब
    0.38
    ał
    0.38
    POSITIVE LOGITS
     Americas
    1.32
     Latin
    1.18
    Latin
    1.14
     Latinoamérica
    1.09
     latino
    1.06
     latin
    0.94
     América
    0.92
     Amérique
    0.89
     America
    0.88
     Америки
    0.85
    Activations Density 0.028%

    No Known Activations