© 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. 128436
    Prev
    Next
    INDEX
    Explanations

    javascript imports

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

    This neuron identifies lines that declare module imports (e.g. ES6 “import … from …” statements).

    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
    𝐇
    -1.73
    𝐌
    -1.73
     rédig
    -1.63
     camiset
    -1.62
     estadounid
    -1.62
    unlimited
    -1.61
    ⅗
    -1.58
    behälter
    -1.57
    ⅘
    -1.55
    粜
    -1.55
    POSITIVE LOGITS
     $
    1.72
    ↵↵↵
    1.51
    ↵↵
    1.50
    ğimiz
    1.46
    ↵↵↵↵↵↵↵↵↵↵
    1.45
    1
    1.45
     where
    1.43
    ↵↵↵↵↵↵↵↵↵↵↵
    1.41
     Here
    1.38
     работать
    1.38
    Activations Density 0.027%

    No Known Activations