© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118244
    Prev
    Next
    INDEX
    Explanations

    using or accessing the internet

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

    The neuron fires on words that refer to digital data transmission or network connectivity (e.g. transmit, data, connect, internet, network, modem).

    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
     ofrecer
    -0.83
    cjonal
    -0.82
    dron
    -0.82
    titleMargin
    -0.81
    サーバー
    -0.79
    TryParse
    -0.79
    باش
    -0.78
    bouncycastle
    -0.78
    ដ
    -0.77
     wearer
    -0.76
    POSITIVE LOGITS
     surfing
    2.61
     surf
    2.42
     browsing
    2.41
     accessing
    2.05
     Internet
    1.98
     internet
    1.95
     access
    1.90
     online
    1.86
     browse
    1.80
     Surfing
    1.78
    Activations Density 0.113%

    No Known Activations