© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9222
    Prev
    Next
    INDEX
    Explanations

    technical terms and their function

    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
    Negative Logits
     verwend
    0.48
    増加
    0.45
     ከተ
    0.45
     zlat
    0.45
     slik
    0.45
     favorit
    0.44
     sobr
    0.44
     „
    0.44
     人気
    0.44
     वस्त्र
    0.43
    POSITIVE LOGITS
    负责
    0.54
    设计
    0.52
    模块
    0.49
    结构
    0.46
    要做
    0.46
    对
    0.46
    给
    0.46
     firmware
    0.46
     encoding
    0.45
    责任
    0.45
    Activations Density 0.007%

    No Known Activations