© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47604
    Prev
    Next
    INDEX
    Explanations

    ， followed by word

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ܘܢ
    0.43
    你的
    0.42
    这里的
    0.42
    撕
    0.42
    这个
    0.40
    黴
    0.39
    原料
    0.39
    少数
    0.38
    ני
    0.38
     ವ್ಯಾ
    0.38
    POSITIVE LOGITS
     could
    0.47
    搁
    0.47
     shouldn
    0.45
     könnten
    0.45
    的关键
    0.45
     zudem
    0.43
     möglicherweise
    0.43
    遑
    0.42
     huống
    0.42
     Changing
    0.42
    Activations Density 0.013%

    No Known Activations