© 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. 2030
    Prev
    Next
    INDEX
    Explanations

    slovak words ending in 'a', 'k', 'n', 'é'

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

    Bratislava, Peter Pellegrini

    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
    mě
    0.72
    ға
    0.70
    Př
    0.68
    Ғ
    0.68
    ған
    0.66
    Қ
    0.66
    Ř
    0.64
    dě
    0.64
    лығы
    0.64
    ně
    0.64
    POSITIVE LOGITS
     alebo
    1.40
     všet
    1.38
     keď
    1.32
     podľa
    1.30
     veľ
    1.30
     ďal
    1.30
     väč
    1.29
     tiež
    1.28
     niektor
    1.28
     veľmi
    1.27
    Activations Density 0.006%

    No Known Activations