© 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-65K
    7. 52782
    Prev
    Next
    INDEX
    Explanations

    sometimes or where

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     گئیں
    0.53
    闥
    0.52
    ندہ
    0.49
     shrewd
    0.48
    ید
    0.47
     لیں
    0.47
    رك
    0.46
    عادة
    0.46
     ईरान
    0.46
    นด์
    0.45
    POSITIVE LOGITS
    ↵
    0.54
    l
    0.49
       
    0.47
     hom
    0.46
    kl
    0.46
              
    0.45
    kr
    0.43
    nl
    0.43
               
    0.42
     Kl
    0.42
    Activations Density 0.013%

    No Known Activations