© 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. 116385
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs

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

    This neuron fires on the names of standard library packages (i.e. package-import identifiers like “bytes”, “fmt”, “os” in Go code).

    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
    넋
    -0.94
    鉿
    -0.93
    tados
    -0.92
    Swatch
    -0.92
    Buckets
    -0.91
    DESCRIPCIÓN
    -0.90
    setw
    -0.88
    $$
    -0.88
    ffekt
    -0.88
    ▬▬
    -0.87
    POSITIVE LOGITS
     gier
    0.85
     می‌دهد
    0.82
     quà
    0.81
    监督
    0.80
    Metropolitan
    0.79
     извест
    0.79
    Olu
    0.77
    と言
    0.75
     tandis
    0.74
    輝く
    0.73
    Activations Density 0.013%

    No Known Activations