© 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. 104675
    Prev
    Next
    INDEX
    Explanations

    C# code context

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

    the character "#" when it appears after the letter "c" in programming contexts (specifically "c#" or "C#").

    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
    With
    -3.11
    There
    -2.94
    Not
    -2.92
    "
    -2.88
    It
    -2.86
    Without
    -2.75
    While
    -2.75
    Only
    -2.70
    Using
    -2.70
    Even
    -2.67
    POSITIVE LOGITS
    “
    2.92
    注意事
    2.83
    悭
    2.77
     vijf
    2.58
    神
    2.56
     dando
    2.53
    紲
    2.50
    棡
    2.47
    蟥
    2.44
     Which
    2.36
    Activations Density 0.034%

    No Known Activations