© 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. 10-GEMMASCOPE-RES-131K
    7. 129625
    Prev
    Next
    INDEX
    Explanations

    conditional return

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

    The neuron strongly activates on statement-terminating semicolons in 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_10/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
     about
    -1.70
     of
    -1.68
     which
    -1.61
     is
    -1.61
     never
    -1.50
    Which
    -1.46
     которых
    -1.41
     Which
    -1.38
     böyle
    -1.34
     ถ้า
    -1.32
    POSITIVE LOGITS
    ズニー
    1.36
    优雅
    1.33
    埼玉県
    1.30
    〼
    1.30
    оргаш
    1.28
    沖縄
    1.28
    лежки
    1.28
    グルト
    1.28
    луйста
    1.27
    ỏi
    1.27
    Activations Density 0.008%

    No Known Activations