© 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. 2665
    Prev
    Next
    INDEX
    Explanations

    interaction. Department. protect. today

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

    Gemma team at Google

    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
    ಈ
    0.41
    ৪৯
    0.41
    или
    0.40
    ঢাকা
    0.39
    器官
    0.39
     จาก
    0.39
     органы
    0.38
     nove
    0.38
     taala
    0.38
    铀
    0.38
    POSITIVE LOGITS
    gh
    0.52
     cheg
    0.43
    ₕ
    0.43
     Gh
    0.41
    '.'
    0.40
     Journ
    0.40
     স
    0.39
     adesso
    0.38
     expressly
    0.38
     adipiscing
    0.38
    Activations Density 0.073%

    No Known Activations