© 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. 40687
    Prev
    Next
    INDEX
    Explanations

    database find and populate operations

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

    The neuron fires on Mongoose (and similar) query‐API calls and their chaining (e.g. `.find()`, `.populate()`, `.exec()`, `.then()`, `.findOne()`).

    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
    Dichloroprop
    -1.20
     rapor
    -1.18
     gymnas
    -1.18
    ⎮
    -1.17
     soudain
    -1.17
    ystemen
    -1.17
     стране
    -1.17
     arv
    -1.16
    similar
    -1.15
    ☆☆☆☆
    -1.15
    POSITIVE LOGITS
     zeker
    1.25
     particularly
    1.21
     out
    1.17
     daarna
    1.16
     dönem
    1.13
    Ưu
    1.13
     voldoende
    1.12
     אינו
    1.10
    近期
    1.10
     informó
    1.10
    Activations Density 0.031%

    No Known Activations