© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112338
    Prev
    Next
    INDEX
    Explanations

    programming syntax

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

    code formatting elements like indentation, brackets, and structural syntax in programming snippets.

    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
     this
    -1.92
    ֳ
    -1.50
    ISTRATION
    -1.48
    
    -1.48
     {
    -1.47
     there
    -1.47
    brokes
    -1.47
    ittà
    -1.45
    Enllaços
    -1.44
     möglicherweise
    -1.43
    POSITIVE LOGITS
     then
    2.36
     chré
    1.86
     religieuses
    1.74
     jūsų
    1.74
    だったら
    1.62
    ῖς
    1.58
    ῖν
    1.53
     specifiche
    1.48
    Lalu
    1.48
     サービス
    1.48
    Activations Density 0.656%

    No Known Activations