© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9972
    Prev
    Next
    INDEX
    Explanations

    Laravel token and initialization

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

    The neuron is highly activated by PHP code tokens—especially the backslash namespace separator and related keywords like “use” and class-path strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    php
    0.82
    PHP
    0.80
     PHP
    0.75
     php
    0.73
    mysqli
    0.73
     ".$
    0.72
    ="'.$
    0.71
     '.$
    0.70
    Php
    0.70
    <?=$
    0.70
    POSITIVE LOGITS
     दाख
    0.59
    isin
    0.54
     impl
    0.53
     ucz
    0.53
    impl
    0.53
    aigne
    0.53
     Eintritt
    0.52
     fractal
    0.50
     \
    0.50
     feet
    0.49
    Activations Density 0.000%

    No Known Activations