© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1919
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     акысыз
    0.34
    饮食
    0.31
     берегу
    0.31
     тур
    0.30
     امت
    0.29
     ветра
    0.29
    萘
    0.29
     باید
    0.29
     эш
    0.29
    Hug
    0.29
    POSITIVE LOGITS
     "\
    0.48
    toString
    0.47
     printing
    0.46
     "["
    0.44
    println
    0.44
     $"
    0.43
    "\
    0.42
    印刷
    0.42
     "("
    0.40
     '['
    0.40
    Activations Density 0.336%

    No Known Activations