© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59429
    Prev
    Next
    INDEX
    Explanations

    dictionaries, hashes, objects, tuples

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

    The neuron strongly activates on mentions of dictionary‐like data structures (e.g. “dictionary,” “hash,” “list of dictionaries,” type signatures involving Dictionary) in code or API questions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    🔊
    -1.21
     femei
    -1.09
    GLAS
    -1.09
     विश्वसनीय
    -1.09
     墊
    -1.05
    CacheManager
    -1.05
     with
    -1.05
    ✶
    -1.03
     investiga
    -1.02
     Surve
    -1.02
    POSITIVE LOGITS
     menentukan
    1.13
     (!__
    1.13
     is
    1.13
    G
    1.07
     gjort
    1.05
    blers
    1.05
     เรา
    1.03
    цю
    1.02
     может
    1.02
     liegt
    1.01
    Activations Density 0.071%

    No Known Activations