© 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. 152926
    Prev
    Next
    INDEX
    Explanations

    medical care, reporters for, menus in

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

    multi-lingual word fragments

    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
     vésicules
    0.45
     scallops
    0.45
    接觸
    0.43
     участ
    0.42
     ویر
    0.42
    κ
    0.42
     apertures
    0.41
     intérêt
    0.41
    E
    0.41
     ایل
    0.41
    POSITIVE LOGITS
     আমরা
    0.52
    akam
    0.51
     saddhim
    0.50
    Amend
    0.49
    genCode
    0.49
     aata
    0.48
    শকার
    0.47
    Portfolio
    0.47
    লোড
    0.47
     kabar
    0.47
    Activations Density 0.001%

    No Known Activations