© 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. 10-GEMMASCOPE-RES-131K
    7. 70410
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets and specific words

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

    The neuron fires most strongly on PHP code markers and function‐call tokens (e.g. “<?php”, “print(…)”, “printf(…)”).

    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
    鐐
    -1.99
     Definitely
    -1.91
     下载
    -1.88
    autogui
    -1.88
     alanı
    -1.87
     Können
    -1.84
     damaligen
    -1.83
     Ausrüstung
    -1.79
     Unterrichts
    -1.77
     unwavering
    -1.76
    POSITIVE LOGITS
     juf
    1.78
     Exacts
    1.76
     about
    1.73
     muft
    1.70
    塒
    1.66
    我把
    1.66
     encontró
    1.65
     dante
    1.64
     haji
    1.63
     staffel
    1.63
    Activations Density 0.000%

    No Known Activations