© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59337
    Prev
    Next
    INDEX
    Explanations

    php code headers

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

    This neuron detects PHP code that sends or sets HTTP headers (e.g. calls to the header or setHeader functions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    NDICE
    -1.54
    qxd
    -1.51
    nji
    -1.49
    eſ
    -1.48
     vimos
    -1.47
    はは
    -1.46
     \_
    -1.43
     ซึ่ง
    -1.42
    ulico
    -1.41
     Gains
    -1.41
    POSITIVE LOGITS
    the
    1.79
    D
    1.77
    If
    1.70
    龶
    1.63
     jajaja
    1.58
     materiałów
    1.49
    ければ
    1.48
     laterales
    1.48
    ogues
    1.46
    espejo
    1.45
    Activations Density 0.003%

    No Known Activations