Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 209
    Prev
    Next
    INDEX
    Explanations

    exchange and queues

    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
     RSSSF
    -0.72
    मा
    -0.72
    悵
    -0.71
     Bardzo
    -0.70
    仮面
    -0.69
     Ansch
    -0.69
     AssemblyCulture
    -0.69
     reactivity
    -0.68
    unter
    -0.68
    Scri
    -0.67
    POSITIVE LOGITS
     exchange
    1.52
    exchange
    1.47
    Exchange
    1.33
     Exchange
    1.31
     routing
    1.27
     exchanges
    1.23
    Routing
    1.16
     EXCHANGE
    1.16
    routing
    1.10
    交换
    1.07
    Activations Density 0.014%

    No Known Activations