© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9765
    Prev
    Next
    INDEX
    Explanations

    Sokolow or Sokol names

    np_acts-logits-general · gemini-2.5-flash-lite

    flutter widget lifecycle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bib
    0.39
     glassware
    0.37
    emade
    0.37
    డ్
    0.37
    ຶ່ງ
    0.37
    DriverManager
    0.36
    Ｗ
    0.36
     Madeira
    0.36
    icarbon
    0.35
    쏠
    0.35
    POSITIVE LOGITS
     Widget
    0.59
    Widget
    0.57
     Widgets
    0.52
     widgets
    0.49
    BuildContext
    0.49
    KeyPressed
    0.45
     Function
    0.44
    Function
    0.44
     widget
    0.44
    ValueChanged
    0.44
    Activations Density 0.006%

    No Known Activations