© 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. 34-GEMMASCOPE-RES-131K
    7. 45713
    Prev
    Next
    INDEX
    Explanations

    database connection

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

    This neuron responds to PHP code snippets—in particular the opening “<?php” tag and subsequent PHP/MySQL 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
     Http
    -0.92
    ifolium
    -0.84
     offre
    -0.82
    newRow
    -0.80
    Katso
    -0.79
     Bucure
    -0.79
     قابلیت
    -0.78
     WHEN
    -0.77
    tômes
    -0.77
    utique
    -0.76
    POSITIVE LOGITS
     connection
    1.93
     connect
    1.85
    connect
    1.57
     connecting
    1.48
    connection
    1.39
     connects
    1.37
    Connection
    1.37
     connections
    1.36
     Connection
    1.36
    Connect
    1.34
    Activations Density 0.025%

    No Known Activations