© 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. 66388
    Prev
    Next
    INDEX
    Explanations

    no complaints or problems

    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
    unakan
    -1.02
     různých
    -1.01
     разных
    -1.01
    🫀
    -0.94
     різних
    -0.92
     różnych
    -0.91
     mépris
    -0.91
    crito
    -0.90
     uży
    -0.90
     джере
    -0.90
    POSITIVE LOGITS
    aneity
    0.98
     everything
    0.98
     here
    0.98
     this
    0.96
    ناء
    0.94
     overall
    0.91
     zwart
    0.90
    ，「
    0.90
     that
    0.90
     really
    0.89
    Activations Density 0.004%

    No Known Activations