© 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. 72853
    Prev
    Next
    INDEX
    Explanations

    relative path imports

    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
    e
    -2.36
     it
    -2.23
     самая
    -2.02
    o
    -2.02
    or
    -2.00
    ↵↵
    -1.95
     When
    -1.88
    
    -1.80
     worrying
    -1.80
    瘣
    -1.77
    POSITIVE LOGITS
    觧
    2.63
    潆
    2.47
    苼
    2.45
    䊏
    2.41
    ابراین
    2.30
    鸶
    2.27
    寕
    2.25
    isième
    2.23
     \_
    2.20
    𖧵
    2.20
    Activations Density 0.003%

    No Known Activations