© 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. 32959
    Prev
    Next
    INDEX
    Explanations

    $_POST form submissions

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

    The neuron activates on tokens involved in HTTP POST handling (e.g. “post”, “posts”, “posting”, “$_POST”, “POST”, “REQUEST”), so it’s looking for code or discussion about submitting or processing POST requests.

    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
    adalu
    -0.78
    <>(
    -0.77
    ścic
    -0.77
     his
    -0.74
    пии
    -0.73
    స్
    -0.73
    チール
    -0.73
     Norte
    -0.72
    abancı
    -0.70
    sihan
    -0.69
    POSITIVE LOGITS
     POST
    2.45
    POST
    2.38
     post
    2.14
     submitted
    1.98
    post
    1.82
    Post
    1.66
     Post
    1.64
     posted
    1.64
    =$_
    1.59
     submit
    1.57
    Activations Density 0.089%

    No Known Activations