© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32976
    Prev
    Next
    INDEX
    Explanations

    figure citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     on
    -1.98
     from
    -1.74
     you
    -1.68
     of
    -1.54
     to
    -1.50
     in
    -1.48
     by
    -1.48
    pions
    -1.41
     with
    -1.23
     your
    -1.23
    POSITIVE LOGITS
    توضیحات
    1.86
    معرفی
    1.77
    Pengertian
    1.74
    مقدمه
    1.65
    Ꮠ
    1.61
    Penjelasan
    1.55
    Berdasarkan
    1.54
    Langkah
    1.53
    Опис
    1.52
    Spesifikasi
    1.51
    Activations Density 0.000%

    No Known Activations