© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 88585
    Prev
    Next
    INDEX
    Explanations

    system

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

    systematic frameworks

    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_31_width_262k_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
    ين
    0.91
     نتيجة
    0.89
    لي
    0.88
     tím
    0.88
    اية
    0.81
    íti
    0.80
    ك
    0.80
    é
    0.80
     غير
    0.79
     dú
    0.78
    POSITIVE LOGITS
    System
    1.57
    システム
    1.51
     system
    1.50
     सिस्टम
    1.46
    SYSTEM
    1.46
     System
    1.44
     시스템
    1.43
    Sistema
    1.43
    system
    1.41
    시스템
    1.41
    Activations Density 0.105%

    No Known Activations