© 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. 113219
    Prev
    Next
    INDEX
    Explanations

    when you see

    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
     with
    -2.00
     They
    -1.84
    {
    -1.75
     which
    -1.73
     first
    -1.71
     It
    -1.66
    -1.65
     If
    -1.63
     who
    -1.60
    Are
    -1.55
    POSITIVE LOGITS
     deko
    1.80
     katk
    1.72
     uchun
    1.63
     dakika
    1.62
     harita
    1.61
     spesifik
    1.61
    yim
    1.61
     hırka
    1.59
     kupa
    1.59
     kutu
    1.59
    Activations Density 0.017%

    No Known Activations