© 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. 81585
    Prev
    Next
    INDEX
    Explanations

    exceeding U.S. dollars

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

    lost things and messages

    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
     sayı
    0.58
     сложные
    0.56
    igamma
    0.54
    渶
    0.54
    بلا
    0.53
    سلم
    0.52
     חיי
    0.50
    مو
    0.50
     وإ
    0.49
     کبھی
    0.49
    POSITIVE LOGITS
    t
    0.46
     t
    0.45
    ｔ
    0.43
    ugging
    0.43
     Based
    0.43
     Vegetable
    0.42
     JH
    0.42
     Verd
    0.42
    dport
    0.42
     Hemisphere
    0.41
    Activations Density 0.000%

    No Known Activations