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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4921
    Prev
    Next
    INDEX
    Explanations

    Turkish place names and projects

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

    Turkish language and İstanbul

    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
    college
    0.43
    เรีย
    0.42
    优质
    0.41
    美品
    0.41
    Ꭳ
    0.41
    computing
    0.40
    各位同學
    0.40
     intrepid
    0.40
    getCql
    0.39
     الطيب
    0.39
    POSITIVE LOGITS
     İ
    1.49
    İ
    1.48
     İstanbul
    1.45
     İn
    1.44
    İstanbul
    1.33
     İs
    1.27
     Ç
    1.26
     Ş
    1.25
     İzmir
    1.25
     ı
    1.24
    Activations Density 0.089%

    No Known Activations