© 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. 104539
    Prev
    Next
    INDEX
    Explanations

    programming terms and code snippets

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

    programming-related content, particularly in technical Q&A contexts about code, variables, functions, and programming concepts.

    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
     depois
    -1.67
     onOptions
    -1.64
     »
    -1.57
    «
    -1.54
     após
    -1.50
     «
    -1.50
     rowspan
    -1.49
     demasiado
    -1.46
     dos
    -1.45
     Schwerpunkt
    -1.45
    POSITIVE LOGITS
     chrétien
    2.03
     triomphe
    1.53
    背影
    1.52
     scelte
    1.52
     citazioni
    1.51
    Carreira
    1.50
     siè
    1.50
     chré
    1.47
     egenskaper
    1.45
     necessarie
    1.45
    Activations Density 1.691%

    No Known Activations