© 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. 118588
    Prev
    Next
    INDEX
    Explanations

    Cisco routers and optical transport

    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
     Conversation
    -0.85
     Об
    -0.77
    conversation
    -0.71
    ਰਾ
    -0.67
     porque
    -0.67
     tratando
    -0.67
    zerw
    -0.66
    tillery
    -0.66
    ыр
    -0.66
     conversation
    -0.66
    POSITIVE LOGITS
     routers
    0.97
    Release
    0.81
    됐
    0.78
     distraught
    0.77
     doctrina
    0.77
     router
    0.77
    𝑳
    0.75
    Metro
    0.75
     forwards
    0.73
     lantern
    0.72
    Activations Density 0.021%

    No Known Activations