© 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. 22-GEMMASCOPE-RES-131K
    7. 392
    Prev
    Next
    INDEX
    Explanations

    documentation section breaks

    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_22/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
     just
    -0.91
     get
    -0.91
     просто
    -0.81
     used
    -0.81
     Best
    -0.80
    進入
    -0.79
    ？　
    -0.78
    дует
    -0.78
     Like
    -0.76
    ovan
    -0.76
    POSITIVE LOGITS
     jusqu
    1.03
    取决
    0.97
     渋谷
    0.96
    ḿ
    0.95
    áček
    0.93
    iligen
    0.93
    
    0.91
    umentación
    0.91
     midst
    0.90
    unno
    0.90
    Activations Density 0.061%

    No Known Activations