© 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. 22-GEMMASCOPE-RES-131K
    7. 13118
    Prev
    Next
    INDEX
    Explanations

    Python and Javascript imports

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

    The neuron activates on the curly‐brace tokens (“{” and “}”) in JavaScript/TypeScript import statements, i.e. named (destructured) imports.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     vecchi
    -1.00
     successivo
    -0.98
    enaam
    -0.94
    甃
    -0.93
     tunik
    -0.93
     zucca
    -0.93
     groet
    -0.91
     buoni
    -0.91
     filosof
    -0.91
    𝐅
    -0.90
    POSITIVE LOGITS
     that
    1.17
     at
    1.09
     just
    1.03
     tilbake
    1.01
     an
    0.97
     only
    0.97
     what
    0.95
     and
    0.95
     after
    0.95
     most
    0.94
    Activations Density 0.010%

    No Known Activations