© 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. 9067
    Prev
    Next
    INDEX
    Explanations

    professional decisions

    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
     слегка
    0.41
    Wenn
    0.36
    ༠
    0.36
    ཎ
    0.35
     약간
    0.34
     থাকিলেও
    0.34
    焼
    0.34
    निम्नलिखित
    0.34
    疑似
    0.33
     เพิ่ม
    0.33
    POSITIVE LOGITS
     naš
    0.33
     undoubtedly
    0.33
    ↵
    0.32
     sådan
    0.32
     our
    0.32
      
    0.31
     ourselves
    0.30
     [
    0.30
     certainly
    0.30
     continue
    0.29
    Activations Density 0.073%

    No Known Activations