© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14873
    Prev
    Next
    INDEX
    Explanations

    type declarations

    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
     then
    -2.30
    未来
    -1.66
    注意
    -1.63
     will
    -1.62
    Cartney
    -1.54
     using
    -1.52
     ultimi
    -1.49
    用
    -1.48
    幻
    -1.47
    添加
    -1.44
    POSITIVE LOGITS
     that
    1.89
    -
    1.84
     trabajado
    1.58
     honlap
    1.56
     какво
    1.56
     naszej
    1.54
    ったのは
    1.51
    玙
    1.50
     какъ
    1.49
     intentando
    1.49
    Activations Density 0.020%

    No Known Activations