© 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. 63916
    Prev
    Next
    INDEX
    Explanations

    tcp protocol

    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
     obtuse
    -0.77
    жай
    -0.77
    火影
    -0.75
    bians
    -0.73
     horny
    -0.73
     declarative
    -0.71
     Employed
    -0.70
     SFP
    -0.70
    oquia
    -0.69
    getInventory
    -0.69
    POSITIVE LOGITS
     protocol
    0.98
     Proto
    0.91
    Proto
    0.89
     total
    0.88
     PROTO
    0.87
    FLAGS
    0.87
     Protocol
    0.85
     Flags
    0.85
     src
    0.84
     protocols
    0.84
    Activations Density 0.010%

    No Known Activations