© 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. 11187
    Prev
    Next
    INDEX
    Explanations

    markup and code syntax

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

    closing braces or semicolons that end function definitions in code.

    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
    神情
    -2.11
    满脸
    -2.06
    だけ
    -1.91
     zowel
    -1.85
    转头
    -1.84
    笑容
    -1.84
     kee
    -1.78
     first
    -1.77
    脸上的
    -1.75
     "";
    -1.74
    POSITIVE LOGITS
     when
    2.44
     if
    2.36
    y
    2.13
    </h2>
    2.06
    ).
    2.03
    >
    2.02
    [
    1.96
     because
    1.95
     with
    1.84
    >
    1.82
    Activations Density 0.004%

    No Known Activations