© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49160
    Prev
    Next
    INDEX
    Explanations

    interface declarations

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

    The neuron is looking for TypeScript/JavaScript module import/export syntax—especially the curly‐brace tokens (“{” and “}”), the import/export keywords, and the path separators in module paths.

    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
    Thus
    -0.90
    hető
    -0.85
    Usually
    -0.84
    洗浄
    -0.83
     аромат
    -0.83
    Surely
    -0.82
    igable
    -0.81
     rapporte
    -0.78
    entable
    -0.76
    demies
    -0.75
    POSITIVE LOGITS
     interface
    1.11
     interfaces
    0.98
     const
    0.96
     let
    0.86
     tslint
    0.83
    let
    0.82
    interfaces
    0.81
     ihrer
    0.81
    const
    0.81
    fiscal
    0.79
    Activations Density 0.011%

    No Known Activations