© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129148
    Prev
    Next
    INDEX
    Explanations

    exception handling

    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
     diki
    -1.64
     tarn
    -1.55
    خخ
    -1.50
     russo
    -1.40
     Luar
    -1.39
     Buat
    -1.35
     Soal
    -1.34
     divino
    -1.34
     défauts
    -1.34
     çi
    -1.32
    POSITIVE LOGITS
     to
    1.90
     not
    1.87
     It
    1.84
     In
    1.52
     is
    1.48
     покрытие
    1.45
     befinden
    1.43
     entsprechenden
    1.41
     either
    1.40
     وت
    1.40
    Activations Density 0.005%

    No Known Activations