© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82894
    Prev
    Next
    INDEX
    Explanations

    php code and comments

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

    The neuron detects standalone numeric literals (integer constants) embedded 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_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
     function
    -1.00
    funktionen
    -0.90
     функции
    -0.88
    끫
    -0.86
     eenen
    -0.84
     pazienti
    -0.84
     音乐
    -0.81
    けると
    -0.80
     沈
    -0.79
    清空
    -0.79
    POSITIVE LOGITS
    /**
    1.19
     list
    1.16
    list
    1.16
     lists
    0.95
    なか
    0.93
    [$
    0.86
    try
    0.85
     without
    0.84
    lists
    0.84
     список
    0.81
    Activations Density 0.009%

    No Known Activations