© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176432
    Prev
    Next
    INDEX
    Explanations

    specific entities or concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    identify potential errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     한다
    0.54
     सत्
    0.54
     zdroj
    0.54
     ܡ
    0.53
     ಶಾ
    0.52
     করার
    0.51
     فيلم
    0.50
     กราบ
    0.50
     然后
    0.50
     करने
    0.49
    POSITIVE LOGITS
     aeron
    0.48
    בין
    0.48
    باش
    0.45
     disusun
    0.44
     Aeron
    0.42
    
    0.42
    Fair
    0.41
    اعل
    0.41
    kate
    0.41
    امر
    0.39
    Activations Density 0.000%

    No Known Activations