© 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. 2415
    Prev
    Next
    INDEX
    Explanations

    print, cout, println, log

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

    printing output

    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
    িখিত
    0.41
     Wellesley
    0.41
    鄴
    0.39
     Horton
    0.39
     Swezey
    0.38
     تړل
    0.38
     }}^{\
    0.37
     विकिरण
    0.37
     খুঁজ
    0.37
     কাউকে
    0.36
    POSITIVE LOGITS
    ("\
    1.19
    "\
    1.12
    ("--------
    1.12
     "\
    1.09
    println
    1.05
    ('\
    0.97
     println
    0.95
    ("***
    0.95
    Println
    0.94
     "*************
    0.94
    Activations Density 0.002%

    No Known Activations