© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5405
    Prev
    Next
    INDEX
    Explanations

    cleaning and family

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

    leet speak and encoded text

    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
     Когда
    0.48
    Еще
    0.48
     Кстати
    0.47
    Cette
    0.46
    Когда
    0.45
     Первая
    0.44
    Источник
    0.44
    ᑉ
    0.44
    Спасибо
    0.42
     Перейти
    0.42
    POSITIVE LOGITS
     s
    0.63
     l
    0.63
     r
    0.62
     p
    0.62
     progr
    0.61
     con
    0.60
     m
    0.60
     f
    0.59
     probl
    0.57
     o
    0.57
    Activations Density 0.059%

    No Known Activations