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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117862
    Prev
    Next
    INDEX
    Explanations

    The Go Authors

    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
     býval
    -0.72
    formerly
    -0.71
    stb
    -0.71
     Chamberlain
    -0.69
     entreg
    -0.67
     verbe
    -0.66
    耀
    -0.66
    newState
    -0.66
     Pokud
    -0.66
     conjunto
    -0.65
    POSITIVE LOGITS
     sanguine
    0.71
    sscanf
    0.70
     一般
    0.68
     oratory
    0.66
     outlaw
    0.66
     catalogs
    0.66
     warran
    0.66
    チャー
    0.66
    キャンセル
    0.66
    gui
    0.65
    Activations Density 0.065%

    No Known Activations