© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2641
    Prev
    Next
    INDEX
    Explanations

    Uzbek language greetings and phrases

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

    Russian and Uzbek words

    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
    𝓮
    0.63
    ających
    0.60
    reflectionMap
    0.60
     পৃথিবী
    0.59
    𝔀
    0.59
     كوساين
    0.57
    ują
    0.56
    谔
    0.56
    𝐰
    0.55
    śred
    0.55
    POSITIVE LOGITS
     yoki
    1.19
     ishlab
    1.17
     uchun
    1.09
     sifatida
    1.09
     қ
    1.07
     tomonidan
    1.06
     кў
    1.05
     tarix
    1.04
     қў
    0.99
     ikki
    0.98
    Activations Density 0.005%

    No Known Activations