© 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. 78349
    Prev
    Next
    INDEX
    Explanations

    proxy and network circumvention

    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
    ogli
    -0.82
     Италијани
    -0.73
     Unidas
    -0.73
    מ
    -0.73
     चाहता
    -0.73
    POST
    -0.72
     nije
    -0.71
    Scoped
    -0.71
    itou
    -0.70
    理事
    -0.69
    POSITIVE LOGITS
    ssr
    0.91
    Clash
    0.88
    socks
    0.87
    ᅧ
    0.85
     proxies
    0.85
    Wg
    0.84
    Edo
    0.83
    TUN
    0.82
     proxy
    0.81
     Prox
    0.80
    Activations Density 0.030%

    No Known Activations