© 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-16K
    7. 7854
    Prev
    Next
    INDEX
    Explanations

    actions about oneself and knowledge

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    规定
    0.36
    𐰚
    0.35
    投放
    0.35
    र्ग
    0.34
    आज
    0.34
     berücksichtigt
    0.34
    ﻜ
    0.34
    ಗ್
    0.34
    식회사
    0.34
     लिखी
    0.34
    POSITIVE LOGITS
     oneself
    1.54
     kişinin
    0.77
    让人
    0.76
     kita
    0.73
     자신의
    0.73
    自分の
    0.71
    讓人
    0.71
     seseorang
    0.67
     člov
    0.66
    让自己
    0.66
    Activations Density 0.429%

    No Known Activations