© 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. 110694
    Prev
    Next
    INDEX
    Explanations

    license pages or technical pages

    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
     Moreover
    -0.96
     vs
    -0.95
     तथा
    -0.87
     tbsp
    -0.82
     his
    -0.81
     हे
    -0.79
     plus
    -0.78
     zaczą
    -0.77
    Moreover
    -0.77
     Wappen
    -0.75
    POSITIVE LOGITS
     pages
    2.05
     page
    1.64
    pages
    1.29
     pagine
    1.22
     páginas
    1.16
     página
    1.16
    页面
    1.07
     페이지
    1.06
    ():
    1.01
    page
    1.00
    Activations Density 0.004%

    No Known Activations