© 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. 25908
    Prev
    Next
    INDEX
    Explanations

    background processes and programs

    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
    霆
    -0.87
    ностей
    -0.85
    bewerken
    -0.79
    вић
    -0.79
     seria
    -0.78
    TabbedPane
    -0.77
    imura
    -0.76
    switchTo
    -0.76
     '\\;'
    -0.75
    ispiele
    -0.74
    POSITIVE LOGITS
     background
    1.36
     Background
    1.21
    background
    1.17
    Background
    1.15
     processes
    1.13
     BACKGROUND
    1.03
     conflicting
    1.01
     programs
    1.00
     conflict
    0.99
     silently
    0.98
    Activations Density 0.050%

    No Known Activations