© 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. 6811
    Prev
    Next
    INDEX
    Explanations

    go package imports

    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
    Negative Logits
     duong
    -1.68
    无论是
    -1.66
     Ă
    -1.63
    尢
    -1.63
     realizó
    -1.55
     haremos
    -1.52
     ⇒
    -1.52
     formó
    -1.48
    鑁
    -1.47
     then
    -1.46
    POSITIVE LOGITS
    This
    1.94
    These
    1.74
    Also
    1.56
    With
    1.52
     These
    1.48
    Now
    1.48
     What
    1.47
    3
    1.47
    ↵↵
    1.47
     festen
    1.44
    Activations Density 0.018%

    No Known Activations