© 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. 232517
    Prev
    Next
    INDEX
    Explanations

    after punctuation or possessives

    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
    )."
    0.44
    يو
    0.41
     عبدال
    0.40
     例如
    0.40
    nicu
    0.40
     hagg
    0.40
     ↑
    0.40
     knelt
    0.40
    ستين
    0.39
    ياً
    0.39
    POSITIVE LOGITS
    cm
    0.60
    cepat
    0.54
    ्वी
    0.50
     Fmat
    0.48
    dataSource
    0.48
    лефон
    0.48
    ds
    0.47
    cium
    0.46
    =#
    0.46
    ключа
    0.46
    Activations Density 0.001%

    No Known Activations