© 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. 56554
    Prev
    Next
    INDEX
    Explanations

    user dialogue data

    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
     dernières
    0.48
    льности
    0.46
     mün
    0.45
     kommt
    0.45
     Xamarin
    0.44
    ាតុ
    0.44
     climbed
    0.44
     韓国
    0.43
     eus
    0.43
     Е
    0.43
    POSITIVE LOGITS
    표
    0.49
    fol
    0.49
    veyard
    0.47
    에는
    0.46
    상은
    0.46
    emy
    0.45
    faux
    0.45
    Emotional
    0.45
    Box
    0.45
    상
    0.44
    Activations Density 0.003%

    No Known Activations