© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20752
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     dezelve
    -1.55
    颪
    -1.55
     campeón
    -1.52
    鲩
    -1.48
    </em>
    -1.48
    dicionado
    -1.46
    ='';
    -1.46
    ๕
    -1.46
    ๘
    -1.45
     Bourgogne
    -1.44
    POSITIVE LOGITS
     aš
    1.46
    اقرأ
    1.46
    replyreport
    1.45
     five
    1.41
    সূত্র
    1.39
     dabar
    1.38
     albeit
    1.38
     impressively
    1.38
    スポンサーリンク
    1.37
     vandens
    1.37
    Activations Density 0.344%

    No Known Activations