© 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. 22670
    Prev
    Next
    INDEX
    Explanations

    spectator venues and events

    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
    shirts
    -1.26
     Nachdem
    -1.21
     =
    -1.20
    poto
    -1.20
     Sobald
    -1.18
     that
    -1.18
     Finally
    -1.13
    racite
    -1.10
    ჻
    -1.09
    ائية
    -1.08
    POSITIVE LOGITS
     constate
    1.16
     costru
    1.05
     citoyens
    1.05
     stroom
    1.05
     zake
    1.02
     watching
    1.02
    russian
    1.02
     PROVIDE
    1.01
     italie
    1.01
    necess
    1.01
    Activations Density 0.037%

    No Known Activations