© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75882
    Prev
    Next
    INDEX
    Explanations

    schema registration and methods

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

    The neuron fires on Mongoose “MissingSchemaError” messages—specifically the “Schema hasn’t been registered for model” error text.

    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
     smör
    -0.94
    مق
    -0.82
     Pust
    -0.79
     sendMessage
    -0.77
     Hemis
    -0.77
     becau
    -0.76
     strö
    -0.74
    xox
    -0.74
     stör
    -0.74
     Drums
    -0.73
    POSITIVE LOGITS
    methods
    1.15
     static
    1.09
    Methods
    1.04
     virtual
    1.04
     methods
    1.00
     Methods
    0.98
    statics
    0.93
     pre
    0.90
     Virtual
    0.88
    persky
    0.86
    Activations Density 0.006%

    No Known Activations