© 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. 3071
    Prev
    Next
    INDEX
    Explanations

    backend servers and endpoints

    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
     Valentina
    -0.88
     proxies
    -0.85
     lü
    -0.83
    DNS
    -0.83
     proxy
    -0.83
    proxy
    -0.81
     CDN
    -0.81
    CDN
    -0.77
     DNS
    -0.74
     VPN
    -0.73
    POSITIVE LOGITS
    healthy
    0.89
    backend
    0.81
    iths
    0.81
    Backend
    0.79
    backends
    0.79
     acceptor
    0.76
    вающих
    0.76
     backend
    0.73
     rule
    0.71
     ヴィ
    0.71
    Activations Density 0.037%

    No Known Activations