© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7144
    Prev
    Next
    INDEX
    Explanations

    Turkish sentences and phrases

    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
    ไป
    0.55
    า
    0.53
     гуляць
    0.52
     ファン
    0.50
     рэгістрацыі
    0.48
    จะ
    0.48
    เลข
    0.48
    อยู่
    0.48
    ้
    0.48
    เครื่อง
    0.47
    POSITIVE LOGITS
    İ
    1.09
     İ
    1.03
     kaynak
    0.96
     İn
    0.96
    Ş
    0.93
    ğ
    0.93
     yeni
    0.93
    Toplam
    0.92
    İlk
    0.92
    ın
    0.91
    Activations Density 0.001%

    No Known Activations