© 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. 22-GEMMASCOPE-RES-131K
    7. 127884
    Prev
    Next
    INDEX
    Explanations

    our and we statements

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     their
    -1.64
     those
    -1.61
     four
    -1.52
     two
    -1.49
     three
    -1.48
     because
    -1.45
     five
    -1.39
     eight
    -1.38
     this
    -1.31
     several
    -1.31
    POSITIVE LOGITS
     também
    1.21
     también
    1.20
     également
    1.18
     ρ
    1.12
    also
    1.11
    ueel
    1.09
    Similar
    1.09
    を行い
    1.08
    色んな
    1.07
     عمليات
    1.06
    Activations Density 0.001%

    No Known Activations