© 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-16K
    7. 6400
    Prev
    Next
    INDEX
    Explanations

    an followed by nouns starting with a or i

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    υ
    0.68
    その
    0.65
    Num
    0.56
    用
    0.54
    ي
    0.53
    يا
    0.52
    Img
    0.52
     তথা
    0.52
    to
    0.52
    ver
    0.51
    POSITIVE LOGITS
     an
    1.09
     équipe
    0.84
    swering
    0.82
    ä
    0.82
     entrée
    0.79
     école
    0.78
    achron
    0.77
     équipes
    0.75
     unforgettable
    0.75
     antitrust
    0.73
    Activations Density 0.683%

    No Known Activations