© 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. 56672
    Prev
    Next
    INDEX
    Explanations

    after cutoff date

    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
     हिस्सा
    0.43
     画像
    0.42
    ૃત
    0.41
    वण्यात
    0.41
     രാഷ്ട്രീയ
    0.41
     görünt
    0.40
     речь
    0.40
     일부
    0.40
    Ц
    0.40
    基本上
    0.39
    POSITIVE LOGITS
     no
    0.63
     every
    0.60
     optimal
    0.59
     optimizing
    0.53
     all
    0.50
     All
    0.50
     Every
    0.50
     everytime
    0.48
     whether
    0.48
     legumes
    0.48
    Activations Density 0.017%

    No Known Activations