© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23836
    Prev
    Next
    INDEX
    Explanations

    javascript module loading

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

    The neuron fires on mentions of Babel-related module and plugin names (e.g., “babel”, “parser”, “plugin”, “transform”) in code or dependency specs.

    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
    éen
    -0.75
    فض
    -0.73
     Sail
    -0.70
    isDeleted
    -0.68
    ropolitan
    -0.68
    ValueGeneration
    -0.68
    NDR
    -0.68
     ml
    -0.68
     posando
    -0.68
    beria
    -0.67
    POSITIVE LOGITS
     translation
    0.90
     Translation
    0.82
    textwidth
    0.82
    preset
    0.82
    translation
    0.81
     Haver
    0.80
     compiler
    0.78
    otient
    0.78
    babel
    0.78
     gastronom
    0.78
    Activations Density 0.006%

    No Known Activations