© 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. 82606
    Prev
    Next
    INDEX
    Explanations

    tcp/ip network protocols

    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
    手に入
    -0.88
     conduit
    -0.87
    ほ
    -0.82
    ax
    -0.82
     leaps
    -0.81
    队伍
    -0.79
     во
    -0.79
    盎
    -0.77
    </b>
    -0.75
    Ꭲ
    -0.75
    POSITIVE LOGITS
     siège
    0.91
     stroj
    0.90
    皲
    0.89
    dasarkan
    0.86
    dump
    0.85
    FORMANCE
    0.85
     cukru
    0.85
    tcp
    0.84
     külön
    0.83
     escova
    0.83
    Activations Density 0.010%

    No Known Activations