© 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-262K
    7. 9199
    Prev
    Next
    INDEX
    Explanations

    identity groups and affiliations

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    CH
    0.51
    functions
    0.46
     الفيز
    0.40
     জীবের
    0.39
     ändern
    0.39
    而非
    0.39
     বাতিল
    0.38
     অভ্যাস
    0.38
    究
    0.38
    method
    0.38
    POSITIVE LOGITS
     Uhuru
    0.43
     Jokes
    0.43
    ystore
    0.42
     peacefully
    0.42
     caricature
    0.42
     comedian
    0.41
     parlament
    0.41
    នៅក្នុង
    0.41
     eloquently
    0.40
     pastors
    0.39
    Activations Density 0.256%

    No Known Activations