© 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. 73798
    Prev
    Next
    INDEX
    Explanations

    webpack, html, js code

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

    The neuron is detecting mentions of Gulp build‐task pipeline operations (e.g. “gulp,” “task,” “src,” “pipe,” “minify,” “concat,” etc.).

    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
     by
    -1.57
    <bos>
    -1.23
    ”？
    -1.23
     知道
    -1.18
     عندما
    -1.13
    ”!
    -1.13
    лизм
    -1.09
    ?”
    -1.08
     myö
    -1.08
     ”
    -1.07
    POSITIVE LOGITS
    Mostly
    1.31
     여성
    1.19
     ways
    1.18
    filé
    1.18
     entrou
    1.17
     samband
    1.15
     soorten
    1.12
     \&
    1.12
     antigas
    1.11
    饪
    1.11
    Activations Density 0.021%

    No Known Activations