© 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. 10-GEMMASCOPE-RES-131K
    7. 69970
    Prev
    Next
    INDEX
    Explanations

    mongodb

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

    The neuron detects mentions of MongoDB (e.g. “mongodb,” “MongoDb,” “MongoClient,” “Db,” etc.) and flags any token referring to the MongoDB API or database.

    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
     But
    -3.48
    ⑊
    -2.97
     unſ
    -2.95
    ໊
    -2.92
    缡
    -2.88
    ± 
    -2.88
     broader
    -2.80
     jezt
    -2.77
     ſever
    -2.77
     probablement
    -2.77
    POSITIVE LOGITS
    美国的
    2.56
    (
    2.55
    鯓
    2.48
     superbly
    2.19
     supremely
    2.19
     profoundly
    2.17
     exquisitely
    2.17
     strangely
    2.13
     intensely
    2.11
     ”
    2.09
    Activations Density 0.004%

    No Known Activations