© 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. 68571
    Prev
    Next
    INDEX
    Explanations

    money, funds, information

    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
     will
    -1.47
     "
    -1.41
     all
    -1.38
     about
    -1.38
     was
    -1.38
     can
    -1.35
     because
    -1.34
     must
    -1.24
    :"
    -1.23
     always
    -1.23
    POSITIVE LOGITS
     achet
    1.39
     tatouage
    1.30
     nœ
    1.27
    謔
    1.25
     dépens
    1.20
     épar
    1.18
    驀
    1.16
     réinitial
    1.15
    わけではない
    1.12
     voila
    1.10
    Activations Density 0.106%

    No Known Activations