© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32370
    Prev
    Next
    INDEX
    Explanations

    latency and delay

    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
    жо
    -0.81
     pisa
    -0.78
    vänd
    -0.77
     Linde
    -0.74
    ㎡
    -0.73
    锰
    -0.73
     bloed
    -0.71
    +"/"+
    -0.71
    РАВ
    -0.71
     институт
    -0.70
    POSITIVE LOGITS
     latency
    5.13
    latency
    3.83
    Latency
    3.77
     Latency
    3.73
     delay
    3.30
     lag
    3.09
     lat
    3.06
     delays
    2.70
    延迟
    2.61
    delay
    2.55
    Activations Density 0.114%

    No Known Activations