© 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. 90783
    Prev
    Next
    INDEX
    Explanations

    ping and latency

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in spotting numeric expressions—especially standalone numbers and measurement values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    HasForeignKey
    -0.81
    issão
    -0.79
    energies
    -0.78
     semif
    -0.76
    unction
    -0.75
    儡
    -0.74
    +```
    -0.74
     Sorte
    -0.73
     apó
    -0.72
    helin
    -0.72
    POSITIVE LOGITS
     ping
    2.34
     Ping
    1.93
    Ping
    1.83
    ping
    1.77
     pings
    1.60
    PING
    1.53
     latency
    1.44
     lag
    1.35
    latency
    1.23
     tracer
    1.16
    Activations Density 0.037%

    No Known Activations