© 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. 129521
    Prev
    Next
    INDEX
    Explanations

    happening and context

    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
    ዣ
    -1.81
    桖
    -1.74
     cerimonia
    -1.67
     icona
    -1.64
    嵛
    -1.60
    labilir
    -1.57
    fourths
    -1.56
    喈
    -1.56
     otomatis
    -1.55
    entown
    -1.52
    POSITIVE LOGITS
     of
    1.88
     眼
    1.48
     однако
    1.47
    щита
    1.43
     the
    1.42
     throughout
    1.41
     ihres
    1.40
    lás
    1.36
     out
    1.36
     in
    1.36
    Activations Density 0.035%

    No Known Activations