© 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. 103450
    Prev
    Next
    INDEX
    Explanations

    dictionary keys and items

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

    The neuron activates whenever the text mentions Python dictionaries or their common methods/operations (e.g. accessing “dictionary,” calling .keys(), .items(), etc.).

    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
     put
    -0.77
    oltà
    -0.76
    滋味
    -0.73
    hlte
    -0.72
     Silas
    -0.71
     провести
    -0.70
    acek
    -0.68
     Groom
    -0.67
    érance
    -0.67
     ਦੀ
    -0.67
    POSITIVE LOGITS
     keys
    1.45
    keys
    1.40
     items
    1.11
     values
    1.05
    Keys
    1.03
    items
    1.02
    pop
    1.01
     pop
    1.00
     Keys
    0.96
    values
    0.93
    Activations Density 0.011%

    No Known Activations