© 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. 39992
    Prev
    Next
    INDEX
    Explanations

    servlet and web technologies

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

    The neuron is triggered by occurrences of the word “servlet” (i.e. it detects mentions of Java servlets).

    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
    d
    -2.52
    y
    -2.50
    </b>
    -2.41
     ſever
    -2.34
    ↵
    -2.28
    an
    -2.25
    i
    -2.22
    a
    -2.22
     {
    -2.09
    訁
    -2.06
    POSITIVE LOGITS
    鼙
    2.69
    </h3>
    2.66
    ࿆
    2.33
    цию
    2.23
    鳙
    2.23
    servlet
    2.20
     "
    2.11
    VIATIONS
    2.09
    Ｇ
    2.09
    .''
    2.05
    Activations Density 0.000%

    No Known Activations