© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44403
    Prev
    Next
    INDEX
    Explanations

    snapshot views and data copies

    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_10/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
     trabalhadores
    -1.77
     brachten
    -1.66
    來了
    -1.61
     to
    -1.60
     irmãos
    -1.56
     mohli
    -1.55
     praktische
    -1.48
     namorados
    -1.47
     spagno
    -1.47
    同じ
    -1.47
    POSITIVE LOGITS
    点此
    1.54
     mariée
    1.43
    推荐阅读
    1.41
    引言
    1.37
    ※※
    1.36
    ing
    1.35
    ----
    1.35
    ísimo
    1.34
    ဴ
    1.33
     dez
    1.30
    Activations Density 0.095%

    No Known Activations