© 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. 93999
    Prev
    Next
    INDEX
    Explanations

    test and setup definitions

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

    The neuron is detecting code definition keywords (e.g. “def,” “class,” “func”) that introduce functions or classes.

    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
    のかも
    -0.96
    のかもしれません
    -0.93
    ykjav
    -0.92
     disant
    -0.75
     Distrito
    -0.75
     Київ
    -0.75
     frecuente
    -0.73
     шокола
    -0.72
    したもの
    -0.72
    艋
    -0.72
    POSITIVE LOGITS
     test
    1.79
    test
    1.29
     Test
    1.09
     helper
    1.05
     tests
    1.05
    测试
    1.04
     check
    1.02
    確か
    0.95
     Helper
    0.92
     DISABLE
    0.92
    Activations Density 0.006%

    No Known Activations