Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 273
    Prev
    Next
    INDEX
    Explanations

    setup of

    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_16_width_16k_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
    '
    0.65
    ت
    0.62
    ↵↵
    0.60
    تف
    0.56
    গ
    0.56
    لع
    0.55
     Tử
    0.54
    dır
    0.52
    ।।
    0.52
    버
    0.50
    POSITIVE LOGITS
    és
    0.58
    傾向
    0.54
     दोषी
    0.54
     মূল
    0.52
     పూర్తిగా
    0.52
    ୈ
    0.51
     fortale
    0.50
     बिलकुल
    0.50
     unabhängig
    0.49
     publiés
    0.49
    Activations Density 0.001%

    No Known Activations