© 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. 1410
    Prev
    Next
    INDEX
    Explanations

    Lithuanian places and culture

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

    Lithuanian language, news, and humor

    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
     مذہ
    0.58
     نشست
    0.57
    ﯽ
    0.53
    MenuGroup
    0.50
    ﮔ
    0.50
    ԝ
    0.50
    GoObject
    0.49
    BlockUsed
    0.49
     कुछ
    0.49
    InCM
    0.49
    POSITIVE LOGITS
     iš
    1.17
     į
    1.16
     jų
    1.13
    ė
    1.07
     prieš
    1.05
     mūsų
    1.05
     už
    1.05
     mė
    1.04
     dėl
    1.03
     žmog
    1.02
    Activations Density 0.009%

    No Known Activations