© 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. 2474
    Prev
    Next
    INDEX
    Explanations

    check out something

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

    check if

    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
     sucesso
    0.39
    多く
    0.38
     doskona
    0.37
     successo
    0.37
    への
    0.37
     unto
    0.35
    Tis
    0.35
     sucess
    0.35
    हात
    0.35
     하나의
    0.35
    POSITIVE LOGITS
     thoroughly
    1.12
     intently
    1.06
     closely
    1.04
     attentively
    1.02
     carefully
    0.95
    是否有
    0.91
     внима
    0.86
     archives
    0.83
    仔细
    0.83
     extensively
    0.82
    Activations Density 0.330%

    No Known Activations