© 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. 9232
    Prev
    Next
    INDEX
    Explanations

    numbers in code/data contexts

    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
     To
    -2.38
    ところで
    -2.36
    by
    -2.34
    S
    -2.34
    that
    -2.13
     That
    -2.11
    呿
    -2.09
    C
    -2.05
     By
    -2.03
    
    -1.97
    POSITIVE LOGITS
    ↵
    2.50
    ramientas
    2.13
    熥
    2.08
    鯷
    1.99
    ᠷ
    1.95
    枻
    1.94
     adalah
    1.94
    퐸
    1.91
     キーホルダー
    1.89
    峮
    1.87
    Activations Density 0.079%

    No Known Activations