© 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. 10-GEMMASCOPE-RES-131K
    7. 69094
    Prev
    Next
    INDEX
    Explanations

    programming contexts, lists, and code snippets

    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_10/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
     if
    -1.84
     T
    -1.76
     D
    -1.62
     find
    -1.60
     F
    -1.52
     first
    -1.49
     we
    -1.48
     any
    -1.43
     lavish
    -1.41
     longstanding
    -1.41
    POSITIVE LOGITS
     sê
    2.05
    歺
    2.02
    裢
    1.91
    ܖ
    1.84
     zwi
    1.80
     mauva
    1.80
    slightly
    1.78
    
    1.73
     gewi
    1.70
    ჻
    1.68
    Activations Density 0.055%

    No Known Activations