© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 120059
    Prev
    Next
    INDEX
    Explanations

    code blocks and multilingual comments

    np_acts-logits-general · gemini-2.5-flash-lite

    preprocessor directives in code, particularly `#include`, `#region`, `#endregion`, `#define`, `#set`, `#undef`, `#ifdef`, and `#endif`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     every
    -1.82
     and
    -1.77
     each
    -1.66
    今後も
    -1.52
    完全に
    -1.52
    cluse
    -1.50
     than
    -1.48
     وتع
    -1.47
     móds
    -1.43
    日曜日
    -1.41
    POSITIVE LOGITS
     també
    1.74
     भी
    1.71
     usw
    1.54
     werden
    1.52
    	
    1.50
    があります
    1.49
     наших
    1.48
     también
    1.47
     ebenfalls
    1.45
     také
    1.43
    Activations Density 0.001%

    No Known Activations