© 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. 229755
    Prev
    Next
    INDEX
    Explanations

    Bollywood, Kapoor, Krishna

    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
     일반
    0.46
     Vasily
    0.46
     spire
    0.44
    也不是
    0.43
    ники
    0.43
    الغ
    0.42
    不是
    0.42
    שא
    0.41
     타이
    0.40
    袍
    0.40
    POSITIVE LOGITS
    in
    0.48
     Kapoor
    0.48
    innov
    0.48
     बॉलीवुड
    0.47
     mát
    0.47
    inode
    0.47
    মনি
    0.47
    ak
    0.47
     развитию
    0.47
     krishna
    0.47
    Activations Density 0.000%

    No Known Activations