© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14908
    Prev
    Next
    INDEX
    Explanations

    PHP echo statements

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

    The neuron detects PHP echo statements (i.e. uses of the `echo` keyword).

    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
    ،
    -2.73
     они
    -2.52
    .”
    -2.42
     arid
    -2.42
     کرده
    -2.31
    </h4>
    -2.30
     wünschen
    -2.27
     вместе
    -2.20
     ensuing
    -2.19
     They
    -2.17
    POSITIVE LOGITS
    {
    2.34
    ✌
    2.31
    !«
    2.30
    嗞
    2.28
     OGSÅ
    2.27
     DANS
    2.27
    °°
    2.25
    🙃
    2.23
    😄
    2.23
    ~)
    2.22
    Activations Density 0.009%

    No Known Activations