© 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. 54338
    Prev
    Next
    INDEX
    Explanations

    communication 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
     cage
    -0.75
     réservoir
    -0.75
    ographs
    -0.73
    clairage
    -0.70
    きたいと思います
    -0.69
    ских
    -0.69
    URU
    -0.67
    setti
    -0.67
     législ
    -0.67
     kosme
    -0.66
    POSITIVE LOGITS
     protocol
    6.06
     protocols
    5.47
    protocol
    5.00
    Protocol
    4.38
     Protocol
    4.38
    PROTOCOL
    4.25
    protocols
    4.22
     Protocols
    4.13
    协议
    3.95
     protocolo
    3.91
    Activations Density 0.178%

    No Known Activations