© 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. 22-GEMMASCOPE-RES-131K
    4. 69073
    Prev
    Next
    INDEX
    Explanations

    code block closing characters

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

    This neuron detects the PHP closing tag sequence “?>.”

    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
     Dijo
    -1.12
     Многие
    -0.94
    🦃
    -0.93
     quindi
    -0.88
     темно
    -0.87
     различные
    -0.86
     भी
    -0.86
    ÉE
    -0.85
     It
    -0.84
    炒め
    -0.84
    POSITIVE LOGITS
    <eos>
    1.10
    Андрей
    1.06
     bästa
    1.02
     preferências
    0.98
    uride
    0.97
    ANSA
    0.96
    Matéri
    0.95
    ônes
    0.95
    RemindMe
    0.94
    Garantie
    0.94
    Activations Density 0.009%

    No Known Activations