© 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. 10-GEMMASCOPE-RES-131K
    7. 12843
    Prev
    Next
    INDEX
    Explanations

    Wi-Fi, WiMax, WiDi, WiX

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

    The neuron activates on occurrences of the “Wi-” prefix (as in Wi-Fi and related wireless technology terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    i
    -3.14
    ”
    -2.89
    ↵
    -2.66
     pinpoint
    -2.53
     –
    -2.50
    ي
    -2.45
     sizzling
    -2.45
    which
    -2.42
     verstärkt
    -2.42
     empfe
    -2.39
    POSITIVE LOGITS
    𝄆
    2.83
    敺
    2.59
     brille
    2.58
     toscana
    2.55
    戗
    2.53
    ynı
    2.47
    咵
    2.36
     entré
    2.31
    鱟
    2.31
    龗
    2.28
    Activations Density 0.001%

    No Known Activations