© 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. 221190
    Prev
    Next
    INDEX
    Explanations

    update our catalog

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

    growing movement

    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
     choker
    0.48
    ísimo
    0.48
     言っ
    0.46
    NullException
    0.45
     そこ
    0.45
    ित्व
    0.44
     blemishes
    0.44
     ayatan
    0.43
     ちゃっ
    0.43
    َة
    0.43
    POSITIVE LOGITS
    ме
    0.55
    ра
    0.50
    лин
    0.46
    Ray
    0.45
    пере
    0.44
    пря
    0.44
    ще
    0.44
     libertad
    0.43
    飞
    0.43
    రా
    0.42
    Activations Density 0.000%

    No Known Activations