© 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. 31740
    Prev
    Next
    INDEX
    Explanations

    dart code

    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
    ijing
    0.46
    रेडी
    0.42
    মানিক
    0.41
    Burns
    0.40
    mozilla
    0.39
     classe
    0.39
     blaze
    0.38
     제작
    0.38
    زوج
    0.38
    荥
    0.38
    POSITIVE LOGITS
    AppBar
    0.54
    Snackbar
    0.54
    SnackBar
    0.53
    德国
    0.51
    ドイツ
    0.50
     Германии
    0.50
     Germany
    0.49
    德國
    0.49
     German
    0.48
     AppBar
    0.48
    Activations Density 0.048%

    No Known Activations