© 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. 34-GEMMASCOPE-RES-131K
    7. 49310
    Prev
    Next
    INDEX
    Explanations

    php code keywords

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

    The neuron detects invocations of (built-in) PHP functions (i.e. function names followed by parentheses).

    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
     such
    -0.91
     esperti
    -0.85
    떄
    -0.79
     anyone
    -0.79
     söyle
    -0.74
    eu
    -0.72
    йдет
    -0.72
     whoever
    -0.72
     \<
    -0.71
     ресурсы
    -0.71
    POSITIVE LOGITS
    ("
    1.29
    ('
    1.12
     "
    1.03
     Или
    0.95
    olkata
    0.94
     “
    0.93
    ELER
    0.91
    <0xD5>
    0.90
     '
    0.89
     nélkül
    0.88
    Activations Density 0.002%

    No Known Activations