© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106646
    Prev
    Next
    INDEX
    Explanations

    Python sys module

    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
    Not in Any Lists

    No Comments

    Negative Logits
     umowy
    -0.77
     われ
    -0.71
    StrictMode
    -0.71
     Disposal
    -0.69
    づらい
    -0.67
     College
    -0.65
     Scarlet
    -0.65
     архивлан
    -0.65
     entendre
    -0.65
    ريض
    -0.65
    POSITIVE LOGITS
     sys
    5.50
    sys
    5.38
    Sys
    3.41
     Sys
    3.39
     SYS
    3.23
    SYS
    3.08
     syst
    2.70
     Syst
    2.64
     System
    2.48
    System
    2.44
    Activations Density 0.030%

    No Known Activations