© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15762
    Prev
    Next
    INDEX
    Explanations

    medical measurements and abbreviations

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

    This neuron detects programming‐related identifiers and jargon (e.g. class names, service names, framework or API tokens) in code or technical documentation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical programming documentation and code-related content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to Microsoft .NET application development, especially technical prose and code about data models, authentication/services, configuration, and code generation in the enterprise stack.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gorg
    0.55
     IActionResult
    0.55
     Loch
    0.54
     alvo
    0.54
     politician
    0.52
     Gustav
    0.51
     Brist
    0.50
     Thunderbolt
    0.50
     Libert
    0.50
     üt
    0.50
    POSITIVE LOGITS
     প্রতিশ্রুতি
    0.62
     compensating
    0.61
     DbSet
    0.61
    ipotent
    0.57
     Entities
    0.57
    高清
    0.55
    enting
    0.54
     हरिद्वार
    0.54
    odne
    0.53
     शि
    0.53
    Activations Density 0.010%

    No Known Activations