© 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. 31729
    Prev
    Next
    INDEX
    Explanations

    common English words

    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
    
    0.43
    ività
    0.42
     сайте
    0.41
    ícula
    0.40
     মুক্তিব
    0.40
    datum
    0.40
    ')[
    0.39
    ክምና
    0.39
    嘢
    0.39
    នឹង
    0.39
    POSITIVE LOGITS
    ొ
    0.40
     adik
    0.39
     unut
    0.39
    谐
    0.38
    退
    0.37
     ot
    0.37
     imigr
    0.37
    芹
    0.36
    炙
    0.36
     tentunya
    0.35
    Activations Density 0.008%

    No Known Activations