© 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. 34-GEMMASCOPE-RES-131K
    7. 12274
    Prev
    Next
    INDEX
    Explanations

    AWS Lambda functions and packages

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

    The neuron fires strongly on programming language package or module identifiers (e.g. import or dependency strings), particularly those naming AWS Lambda–related libraries.

    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
     Animated
    -0.77
    conci
    -0.73
    brido
    -0.72
     cards
    -0.71
    надцать
    -0.69
    的价格
    -0.69
     supplement
    -0.68
     Supplement
    -0.68
     Height
    -0.68
     leadership
    -0.68
    POSITIVE LOGITS
     ZIP
    0.83
     Overton
    0.82
    Role
    0.79
    HANDLER
    0.78
     pacote
    0.77
    Zip
    0.76
     PACKAGE
    0.74
    PYTHON
    0.74
    role
    0.73
     role
    0.72
    Activations Density 0.025%

    No Known Activations