© 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. 4877
    Prev
    Next
    INDEX
    Explanations

    Afrikaans, Dutch, Belarusian, Cyrillic

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

    Belarusian, Russian, Ukrainian, Haitian Creole

    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
     yoghurt
    0.57
    𝒎
    0.57
     mengurangi
    0.57
    ेंटीना
    0.54
    ﯾ
    0.54
     আমার
    0.52
     khawatir
    0.52
     hacen
    0.51
     maggior
    0.51
     তার
    0.50
    POSITIVE LOGITS
     пры
    1.05
     ў
    1.04
     рэ
    0.96
     гэта
    0.90
    чы
    0.84
    рэ
    0.82
    цыя
    0.80
     тэ
    0.80
    жы
    0.79
     чы
    0.79
    Activations Density 0.006%

    No Known Activations