© 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. 90364
    Prev
    Next
    INDEX
    Explanations

    php code snippets `ini_set` `max_execution_time`

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

    The neuron activates on snippets of source code syntax (notably PHP code tokens and related punctuation).

    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
    roffene
    -0.79
    怼
    -0.76
    crito
    -0.73
    Lewis
    -0.72
     وإن
    -0.72
    SPIN
    -0.72
     Existe
    -0.71
     PartialEq
    -0.71
    コンパクト
    -0.70
    ември
    -0.69
    POSITIVE LOGITS
     ini
    1.27
     @
    1.21
    ini
    1.19
    @
    1.02
    ignore
    0.99
    =@
    0.92
     file
    0.88
     (@
    0.88
     サンダル
    0.86
    ,@
    0.84
    Activations Density 0.043%

    No Known Activations