© 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. 64695
    Prev
    Next
    INDEX
    Explanations

    wireless network access methods

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

    The neuron activates on technical networking jargon, especially terms related to mobile/IP and ad hoc wireless networks.

    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
    ponym
    -0.87
     tapped
    -0.71
    Creative
    -0.66
    தை
    -0.66
    ⊗
    -0.65
    ୀ
    -0.63
     Creative
    -0.63
     Psychos
    -0.63
     vertreten
    -0.62
     Grote
    -0.62
    POSITIVE LOGITS
    网络
    0.82
     Rudd
    0.76
    nikami
    0.76
     куртка
    0.75
     Sever
    0.75
    暢
    0.73
    currentTarget
    0.72
     network
    0.72
     cluster
    0.72
     Angle
    0.71
    Activations Density 0.038%

    No Known Activations