© 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. 90766
    Prev
    Next
    INDEX
    Explanations

    delay and loops

    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
    钕
    -0.75
     信息
    -0.70
    лябин
    -0.69
    Tages
    -0.69
    Heap
    -0.69
    konom
    -0.69
    стъ
    -0.68
    حياته
    -0.68
    ピン
    -0.67
    됩니다
    -0.67
    POSITIVE LOGITS
    loops
    1.05
    DELAY
    1.01
     loops
    0.99
    nop
    0.95
     Delay
    0.94
    delay
    0.91
    asm
    0.91
     Loops
    0.90
    LOOP
    0.88
    Delay
    0.88
    Activations Density 0.011%

    No Known Activations