© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15476
    Prev
    Next
    INDEX
    Explanations

    request followed by objects

    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
     He
    -2.36
     [
    -2.00
     anstatt
    -1.95
     \{
    -1.91
    }{
    -1.80
    ◔
    -1.80
    In
    -1.78
     beziehungs
    -1.77
     It
    -1.77
     einschließlich
    -1.76
    POSITIVE LOGITS
    谖
    2.61
     nových
    2.13
     chiusura
    2.06
    盌
    2.05
    ・・・・・・・・
    2.05
    其妙
    1.98
    勦
    1.98
    ＝＝＝＝
    1.95
     nowych
    1.93
     reizen
    1.93
    Activations Density 0.012%

    No Known Activations