© 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. 1319
    Prev
    Next
    INDEX
    Explanations

    Hungarian suffixes

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

    Hungarian prefixes and suffixes

    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
     Hungarian
    0.62
    匈
    0.62
    ŠE
    0.59
    宻
    0.57
     Estonian
    0.56
     saffron
    0.55
     Ungarn
    0.55
     Hungary
    0.53
     Earlier
    0.53
    洟
    0.53
    POSITIVE LOGITS
    ok
    0.79
    ható
    0.75
    unk
    0.73
    ogat
    0.71
    ért
    0.71
    adás
    0.71
    válto
    0.70
     eredmény
    0.70
    att
    0.68
    tható
    0.68
    Activations Density 0.002%

    No Known Activations