© 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. 205282
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    np_acts-logits-general · gemini-2.5-flash-lite

    curved routes and paths

    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
     network
    0.54
     rownames
    0.50
    不明
    0.49
     tissue
    0.48
     polu
    0.46
    Ꮒ
    0.46
    PMS
    0.46
     these
    0.45
    PPT
    0.45
    प्पी
    0.45
    POSITIVE LOGITS
     поворо
    0.52
     وث
    0.48
     القاعدة
    0.46
     رض
    0.46
     وحد
    0.45
     للح
    0.45
    enbach
    0.44
    .
    0.44
    ıdır
    0.43
     وحده
    0.43
    Activations Density 0.000%

    No Known Activations