© 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. 34-GEMMASCOPE-RES-131K
    7. 65045
    Prev
    Next
    INDEX
    Explanations

    serialization and contracts

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

    The neuron fires on any form of the root “serial” (e.g. “Serialization,” “serialize,” “Serializer,” “BOOST_SERIALIZATION,” 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
    yntaxException
    -0.81
    ASTNode
    -0.76
     ivy
    -0.75
     launch
    -0.73
    訟
    -0.72
     besie
    -0.71
     czarne
    -0.71
     cielo
    -0.71
     spies
    -0.71
     ESPEC
    -0.70
    POSITIVE LOGITS
     Streaming
    1.06
     streaming
    0.94
    DataContract
    0.88
     CONTRACT
    0.79
    streaming
    0.77
    тали
    0.77
    tocin
    0.76
    ký
    0.75
     Serial
    0.73
     Imperial
    0.73
    Activations Density 0.018%

    No Known Activations