© 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. 116759
    Prev
    Next
    INDEX
    Explanations

    efficient and correct execution

    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
     hemen
    -1.05
     periodically
    -0.96
     lắm
    -0.93
     zurückge
    -0.92
     cał
    -0.92
     vulnerables
    -0.92
     sorgfältig
    -0.91
    用于
    -0.90
     randomly
    -0.90
     selten
    -0.90
    POSITIVE LOGITS
     efficiently
    2.17
    efficient
    1.98
     efficient
    1.76
     profitably
    1.62
    Efficient
    1.51
     safely
    1.51
     효
    1.51
     Efficient
    1.49
     correctly
    1.47
    FFICIENT
    1.45
    Activations Density 0.399%

    No Known Activations