© 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. 22-GEMMASCOPE-RES-131K
    7. 98670
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax

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

    This neuron detects lines’ leading indentation (the whitespace at the start of code lines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Then
    -1.09
     then
    -1.02
     kemudian
    -1.01
     então
    -1.00
     everyone
    -0.97
     sehingga
    -0.96
     for
    -0.96
     resistentes
    -0.94
    temuan
    -0.94
     gelap
    -0.94
    POSITIVE LOGITS
    其它
    1.14
    Ḳ
    0.92
    cepcion
    0.91
    (&:
    0.89
    vyk
    0.87
     keď
    0.86
     cuando
    0.83
     chủ
    0.82
    formular
    0.82
     diss
    0.82
    Activations Density 0.002%

    No Known Activations