© 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. 103237
    Prev
    Next
    INDEX
    Explanations

    Kubernetes Authors or k8s.io

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

    The neuron fires strongly on Kubernetes‐related identifiers, version/CVE numbers, API resource kinds and command flags—i.e. tokens specific to Kubernetes configuration, security advisories, and tooling.

    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
     tons
    -0.78
     خلق
    -0.76
    团队
    -0.75
     ")";
    -0.75
     poroz
    -0.74
     ماز
    -0.73
     surn
    -0.73
    jería
    -0.73
     crema
    -0.72
     textil
    -0.71
    POSITIVE LOGITS
    Et
    0.80
    uchtet
    0.79
     Rotate
    0.78
     ARG
    0.75
     του
    0.75
     Unavailable
    0.75
    CADE
    0.74
    гают
    0.72
    TOKEN
    0.72
     скриншот
    0.71
    Activations Density 0.051%

    No Known Activations