© 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. 10-GEMMASCOPE-RES-131K
    7. 100508
    Prev
    Next
    INDEX
    Explanations

    network and socket programming

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

    references to the "System.Net" namespace or "net" import statements in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     the
    -1.83
     rodziny
    -1.77
    ひた
    -1.73
    いただいて
    -1.73
    いって
    -1.68
    衚
    -1.66
    ってしまった
    -1.65
     passou
    -1.65
    がありますが
    -1.64
     each
    -1.62
    POSITIVE LOGITS
     fod
    1.62
     jude
    1.59
     austria
    1.59
    是
    1.55
     oj
    1.52
     syd
    1.52
    ”（
    1.50
     naman
    1.49
    浤
    1.48
     kroner
    1.46
    Activations Density 0.004%

    No Known Activations