© 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. 82299
    Prev
    Next
    INDEX
    Explanations

    world wide web and internet access

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

    The neuron strongly activates on tokens referring to the Internet or Web (e.g. “Web,” “Internet,” “connect,” “Copyscape,” “world‐wide‐web,” etc.).

    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
    neid
    -0.69
    athus
    -0.68
    litt
    -0.68
    ondi
    -0.68
    avid
    -0.68
     propriedade
    -0.68
    žiť
    -0.67
     Deine
    -0.66
    oches
    -0.66
    ney
    -0.66
    POSITIVE LOGITS
     internet
    3.89
     Internet
    3.67
    Internet
    3.33
    internet
    3.23
    互联网
    2.75
    インターネット
    2.75
     INTERNET
    2.59
    INTERNET
    2.39
     internetu
    2.20
     интернет
    2.16
    Activations Density 0.109%

    No Known Activations