© 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. 45491
    Prev
    Next
    INDEX
    Explanations

    negative states, queues, and confinement

    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
     example
    -1.47
     both
    -1.34
     obtained
    -1.23
    .《
    -1.22
     Ma
    -1.20
     differs
    -1.16
     namely
    -1.14
     erstmals
    -1.14
    errMsg
    -1.13
     é
    -1.11
    POSITIVE LOGITS
     for
    1.23
     żeby
    1.22
    cnia
    1.18
    娑
    1.16
     pensar
    1.16
    puted
    1.14
    Там
    1.14
    itis
    1.14
     recevez
    1.13
    няют
    1.12
    Activations Density 0.082%

    No Known Activations