© 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. 22-GEMMASCOPE-RES-131K
    7. 24961
    Prev
    Next
    INDEX
    Explanations

    ASP.NET MVC view code

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     futura
    -1.13
    燧
    -1.05
     違い
    -1.04
    🤮
    -1.00
     ее
    -1.00
     取付
    -1.00
     trovi
    -0.97
     compréhen
    -0.97
     doccia
    -0.96
     abiye
    -0.96
    POSITIVE LOGITS
    ztes
    1.10
     sepenuhnya
    1.09
    бол
    1.07
    ériques
    1.02
    верху
    1.01
    がある
    1.00
    жении
    0.98
     government
    0.96
     могут
    0.94
    yati
    0.94
    Activations Density 0.029%

    No Known Activations