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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5144
    Prev
    Next
    INDEX
    Explanations

    Greece and Greek contexts

    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_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
    큥
    0.55
    톈
    0.52
    亿美元
    0.52
    듑
    0.50
     Chipotle
    0.49
     кирпи
    0.49
    녠
    0.48
    zco
    0.48
     américain
    0.47
    캔
    0.47
    POSITIVE LOGITS
     Greece
    1.54
     Greek
    1.48
     Thessaloniki
    1.40
     Aegean
    1.36
    Greece
    1.33
     greek
    1.27
    Greek
    1.27
     Hellen
    1.23
     PAOK
    1.23
     Griechen
    1.21
    Activations Density 0.049%

    No Known Activations