© 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. 45709
    Prev
    Next
    INDEX
    Explanations

    phrases that pause

    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
     and
    -2.13
     each
    -1.93
     who
    -1.62
    :
    -1.46
     every
    -1.45
     destes
    -1.43
     will
    -1.43
     každé
    -1.38
    </b>
    -1.30
     (
    -1.28
    POSITIVE LOGITS
     memutus
    1.56
     essendo
    1.55
    餍
    1.43
     composants
    1.40
     quæ
    1.34
     isn
    1.34
     polaire
    1.34
     mengatasi
    1.33
    鯔
    1.32
     hasn
    1.30
    Activations Density 0.016%

    No Known Activations