© 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. 58248
    Prev
    Next
    INDEX
    Explanations

    time ago

    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
     as
    -1.47
    Since
    -1.41
     since
    -1.34
     any
    -1.32
     should
    -1.28
     to
    -1.24
    每个
    -1.23
     zowel
    -1.20
     initially
    -1.17
    onenumber
    -1.17
    POSITIVE LOGITS
    recently
    1.69
     recently
    1.46
     recientemente
    1.34
     récemment
    1.30
     RECENT
    1.27
    )|^{
    1.27
     ordem
    1.27
     frage
    1.27
     lately
    1.26
     недавно
    1.26
    Activations Density 0.053%

    No Known Activations