© 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. 87215
    Prev
    Next
    INDEX
    Explanations

    change in dates or services

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

    withdrawn at any time

    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
    Negative Logits
     이번
    0.50
     ав
    0.49
     የሆነ
    0.47
    gou
    0.46
     Վ
    0.45
     сиз
    0.44
    iminary
    0.44
     Кі
    0.43
     Đức
    0.43
     Л
    0.43
    POSITIVE LOGITS
    改變
    0.49
     changé
    0.47
    厠
    0.46
     değişiklik
    0.45
    เปลี่ยน
    0.44
     interfacial
    0.44
    يبقى
    0.43
    ेटा
    0.42
    服務
    0.41
     koju
    0.41
    Activations Density 0.001%

    No Known Activations