© 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. 34-GEMMASCOPE-RES-131K
    7. 47239
    Prev
    Next
    INDEX
    Explanations

    hosting events and guests

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     emphasized
    -0.94
     emphasizing
    -0.94
     zumal
    -0.93
    结论
    -0.92
     hergestellt
    -0.92
     недавно
    -0.91
     protecting
    -0.91
     Estudio
    -0.91
     encompassing
    -0.88
     Enero
    -0.87
    POSITIVE LOGITS
     guests
    1.28
     a
    1.26
     здесь
    1.24
     čet
    1.18
     зді
    1.18
     events
    1.18
     visitors
    1.17
    Leírás
    1.16
    ງ
    1.08
    guests
    1.06
    Activations Density 0.020%

    No Known Activations