© 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. 34-GEMMASCOPE-RES-131K
    7. 57632
    Prev
    Next
    INDEX
    Explanations

    firebase.firestore retrieval methods

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

    The neuron specifically fires on references to Firebase Firestore API calls (e.g. “firebase.firestore().collection”, “get”, 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
    菏
    -0.89
     Customs
    -0.81
    zzato
    -0.80
     junho
    -0.77
     prat
    -0.75
     appar
    -0.74
     RAS
    -0.73
    ategorias
    -0.73
     assum
    -0.72
    istisches
    -0.70
    POSITIVE LOGITS
    doc
    1.22
     doc
    1.21
    Doc
    1.13
     document
    1.04
     where
    0.99
    snapshots
    0.88
     Doc
    0.87
    Document
    0.86
    document
    0.85
     einfachen
    0.84
    Activations Density 0.004%

    No Known Activations