© 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. 61095
    Prev
    Next
    INDEX
    Explanations

    correcting errors or making things correct

    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
    ور
    1.02
    ول
    0.75
     assassin
    0.73
    ){
    0.70
    是一個
    0.66
    การ
    0.65
    ırs
    0.65
    ক
    0.64
     employees
    0.64
    ا
    0.63
    POSITIVE LOGITS
    Cor
    0.92
    Corr
    0.83
     COR
    0.71
    corollary
    0.71
    腐
    0.70
     Kor
    0.70
    Kor
    0.70
    ى
    0.70
    Correct
    0.70
    Кор
    0.69
    Activations Density 0.092%

    No Known Activations