© 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. 34-GEMMASCOPE-RES-131K
    7. 90023
    Prev
    Next
    INDEX
    Explanations

    Visual Studio versions

    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
     Age
    -0.77
    Age
    -0.74
    
    -0.69
    Cream
    -0.69
     предлага
    -0.68
    复制代码
    -0.66
     Сочи
    -0.66
    Games
    -0.66
    мора
    -0.66
     Routing
    -0.65
    POSITIVE LOGITS
     inca
    0.69
     Tuna
    0.68
    ￦
    0.67
    CanBe
    0.67
    rdom
    0.66
     extinguishing
    0.65
     Tribun
    0.63
    insulin
    0.62
     взаимодействия
    0.62
    estal
    0.61
    Activations Density 0.064%

    No Known Activations