© 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. 119844
    Prev
    Next
    INDEX
    Explanations

    testing code contexts

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

    the word "TEST" in source code (variable names, function names, constants, and comments).

    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
    AutoresizingMask
    -2.58
    嗩
    -2.55
    沨
    -2.44
    ୌ
    -2.42
     ");
    -2.39
    好看的
    -2.39
    
    -2.34
     Zweiten
    -2.31
    
    -2.31
    ଃ
    -2.23
    POSITIVE LOGITS
    {
    3.73
    er
    3.45
    ed
    3.30
    ar
    2.84
    en
    2.66
    在一个
    2.58
    涐
    2.45
    ,
    2.42
    al
    2.41
    man
    2.41
    Activations Density 0.001%

    No Known Activations