© 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. 22848
    Prev
    Next
    INDEX
    Explanations

    event details and requirements

    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
     铝
    -1.48
    を変える
    -1.44
    つづく
    -1.40
    鵙
    -1.39
     épaules
    -1.38
     eksklu
    -1.36
    什么样的
    -1.35
    věř
    -1.31
    ětí
    -1.30
     carreaux
    -1.28
    POSITIVE LOGITS
     still
    1.48
     one
    1.40
     so
    1.35
    ？　
    1.33
     can
    1.31
     although
    1.26
    ;
    1.25
     this
    1.23
     són
    1.23
     for
    1.23
    Activations Density 0.066%

    No Known Activations