© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110950
    Prev
    Next
    INDEX
    Explanations

    AWS service namespaces

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron most strongly activates on mentions of AWS service names and related technical terms (e.g. “Amazon,” “ECR,” “Service,” “Limits,” “per,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     악
    -0.82
     restoration
    -0.75
     HTML
    -0.74
    loch
    -0.73
     bucket
    -0.72
     Dux
    -0.72
     autoimmune
    -0.71
     HDMI
    -0.70
     ترکیه
    -0.70
     funcionario
    -0.69
    POSITIVE LOGITS
    ECS
    0.81
     ECS
    0.76
     marines
    0.73
    Task
    0.73
     task
    0.72
     herunter
    0.71
    Closest
    0.70
    ULONG
    0.70
    aturated
    0.70
    任务
    0.70
    Activations Density 0.044%

    No Known Activations