© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7325
    Prev
    Next
    INDEX
    Explanations

    Turkey, Ottoman, Atatürk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    輥
    1.10
     выращи
    1.02
    ﾗ
    1.00
    ುತ್ತವೆ
    1.00
    畤
    1.00
     крупней
    0.98
    MaxIntensity
    0.96
     сцен
    0.95
    ುತ್ತದೆ
    0.92
    チック
    0.92
    POSITIVE LOGITS
     İ
    2.41
    İ
    2.13
     İstanbul
    2.05
     ş
    2.03
     Türkiye
    1.99
     Ş
    1.95
     ı
    1.92
     diğer
    1.90
     baş
    1.89
     İs
    1.88
    Activations Density 0.066%

    No Known Activations