© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3817
    Prev
    Next
    INDEX
    Explanations

    Turkish places and people

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

    Turkey, Istanbul, Atatürk

    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_53_width_65k_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
    เชสเตอร์
    0.55
     راجس
    0.54
     कटोच
    0.54
    されて
    0.52
    คองโก
    0.50
     hydrating
    0.50
     क्विंट
    0.49
    ༞
    0.49
    ーブ
    0.49
     بوتل
    0.49
    POSITIVE LOGITS
     Turkish
    2.53
    Turkish
    2.38
     Istanbul
    2.23
     Ankara
    2.22
     turkish
    2.22
     Türk
    2.20
     İstanbul
    2.17
     türk
    2.17
     Türkiye
    2.16
    Istanbul
    2.14
    Activations Density 0.067%

    No Known Activations