© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76618
    Prev
    Next
    INDEX
    Explanations

    code or technical terms beginnings

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

    The neuron fires on mentions of reflection APIs or namespaces (e.g. “Reflection,” “using System.Reflection,” “import "reflect” 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
    byshire
    -0.83
    firebase
    -0.82
     Simp
    -0.79
     adesivos
    -0.77
    dataflow
    -0.77
     pelu
    -0.75
    DecimalFormat
    -0.74
    ChangeEvent
    -0.73
    fetched
    -0.73
    免费
    -0.73
    POSITIVE LOGITS
    يلة
    0.84
     monasterio
    0.75
    ཀ
    0.74
     reflection
    0.73
    inazione
    0.73
    育て
    0.72
    ogado
    0.72
     coração
    0.72
     PGC
    0.71
     verschiedenen
    0.71
    Activations Density 0.006%

    No Known Activations