© 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. 239866
    Prev
    Next
    INDEX
    Explanations

    our, ourselves, us

    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
    Not in Any Lists

    No Comments

    Negative Logits
    δό
    0.46
    лети
    0.44
    то
    0.43
    니다
    0.42
    SOR
    0.42
    лях
    0.41
    stub
    0.41
    ъ
    0.41
    ”)
    0.41
     unsightly
    0.41
    POSITIVE LOGITS
    '،
    0.45
    🔡
    0.45
     رب
    0.45
    eltat
    0.45
     நண்ப
    0.43
     বন্ধু
    0.43
     nehmen
    0.43
    spiele
    0.43
    nEnter
    0.43
    setzen
    0.43
    Activations Density 0.003%

    No Known Activations