© 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. 127514
    Prev
    Next
    INDEX
    Explanations

    online content, sources

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

    calculations, parts, or relationships

    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
    <0x0D>
    0.52
     is
    0.51
     defines
    0.50
    ک
    0.49
    ي
    0.49
    י
    0.49
    ม
    0.48
     NOTHING
    0.48
    ↵
    0.48
    可
    0.48
    POSITIVE LOGITS
    の特徴
    0.52
     সম্পাদিত
    0.52
    の違い
    0.50
     عرف
    0.49
    oglobin
    0.47
    ڈین
    0.46
     স্বভাব
    0.45
     リン
    0.45
     उत्‍
    0.44
     সম্পূর্ণরূপে
    0.44
    Activations Density 0.000%

    No Known Activations