© 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. 103014
    Prev
    Next
    INDEX
    Explanations

    special, unique, amazing, sparkling

    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
     to
    -2.55
     as
    -1.94
     for
    -1.79
     should
    -1.52
     all
    -1.41
     Because
    -1.40
     are
    -1.39
     Both
    -1.38
     because
    -1.36
     would
    -1.33
    POSITIVE LOGITS
     hoặc
    1.50
     veya
    1.47
    ۱۶
    1.45
    攵
    1.45
     ваш
    1.45
     tirantes
    1.45
     trabajado
    1.41
     atau
    1.39
    ۱۲
    1.39
     étrang
    1.38
    Activations Density 0.115%

    No Known Activations