© 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. 9293
    Prev
    Next
    INDEX
    Explanations

    specifically

    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
    の世界
    0.43
    文件
    0.42
    <unused2130>
    0.41
     العالم
    0.39
     mundo
    0.39
    。
    0.39
     세계
    0.38
    由来
    0.38
    可知
    0.37
    BERT
    0.37
    POSITIVE LOGITS
     Specifically
    0.64
     specifically
    0.58
     konkrét
    0.58
     конкре
    0.55
     específicamente
    0.54
     именно
    0.52
     исключительно
    0.50
     absolutely
    0.49
    実際に
    0.49
     unquestionably
    0.49
    Activations Density 0.047%

    No Known Activations