© 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. 34-GEMMASCOPE-RES-131K
    4. 53850
    Prev
    Next
    INDEX
    Explanations

    programming keywords and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Twelve
    -0.79
     Jobs
    -0.79
    Luis
    -0.77
    Twelve
    -0.77
    isIn
    -0.73
     cups
    -0.72
    Ways
    -0.71
     appendix
    -0.71
    Rs
    -0.70
    James
    -0.69
    POSITIVE LOGITS
     Thrust
    0.71
    Thrust
    0.71
    atina
    0.71
     favourably
    0.68
    JTextField
    0.68
     truthfully
    0.67
     violences
    0.67
     unbelie
    0.67
    getParameter
    0.66
     seclusion
    0.66
    Activations Density 0.534%

    No Known Activations