© 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. 32450
    Prev
    Next
    INDEX
    Explanations

    Entities, configurations, and code generation strategy

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

    The neuron fires on uppercase technical identifiers—configuration keys, constant names, or SQL/ORM directives in code (e.g. CodeGenerationStrategy, IDENTITY_INSERT, JSON, serialization modes).

    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
     cht
    -0.82
    TOUR
    -0.77
    媽
    -0.76
    bewerken
    -0.76
    balanceOf
    -0.76
     khóc
    -0.75
    วัด
    -0.75
    嗜
    -0.75
    ported
    -0.74
    AuxInt
    -0.74
    POSITIVE LOGITS
    artz
    0.90
     vitesses
    0.80
     Guarantee
    0.80
    uuid
    0.79
     recomiendo
    0.78
     scheme
    0.77
    менение
    0.77
     CLOCK
    0.76
    nvarchar
    0.75
    ाद
    0.75
    Activations Density 0.001%

    No Known Activations