© 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. 102171
    Prev
    Next
    INDEX
    Explanations

    diagonals

    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
    这个
    -2.41
    结语
    -2.16
    你
    -2.08
    ሷ
    -2.03
     récentes
    -1.91
    それを
    -1.91
    و
    -1.90
    We
    -1.89
     publicitaires
    -1.89
    我们的
    -1.88
    POSITIVE LOGITS
     the
    2.39
     alberga
    2.11
     here
    1.91
    
    1.91
     least
    1.84
    唧
    1.82
    ような
    1.81
    ferrous
    1.81
    可不是
    1.80
    కర్య
    1.80
    Activations Density 0.003%

    No Known Activations