© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78635
    Prev
    Next
    INDEX
    Explanations

    vpn and privacy

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     després
    -0.88
     آورد
    -0.87
     poliéster
    -0.87
     Datenbank
    -0.80
    WEBPACK
    -0.80
     instagram
    -0.79
     croce
    -0.79
     промо
    -0.79
     太陽
    -0.79
     speaker
    -0.79
    POSITIVE LOGITS
     VPN
    2.13
    VPN
    1.80
    vpn
    1.55
     vpn
    1.42
     tunneling
    1.31
     privacy
    1.20
     anonymity
    1.13
    privacy
    1.05
     tunne
    1.04
     torrent
    1.02
    Activations Density 0.013%

    No Known Activations