© 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. 129931
    Prev
    Next
    INDEX
    Explanations

    mongodb

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

    The neuron fires on code‐snippet tokens referring to MongoDB (and its credentials), e.g. “mongodb,” “cred,” and “creds.”

    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
    *
    -4.34
    ي
    -3.56
    i
    -3.38
    ?
    -3.19
    狴
    -2.86
    
    -2.50
    that
    -2.38
    5
    -2.36
    ↵↵
    -2.34
    ి
    -2.34
    POSITIVE LOGITS
     Ganzen
    2.84
    🫓
    2.77
    𝟴
    2.70
    
    2.64
    龊
    2.59
     otras
    2.56
     ewigen
    2.56
     Allgemeinen
    2.52
    。“
    2.52
    ╿
    2.50
    Activations Density 0.007%

    No Known Activations