© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12408
    Prev
    Next
    INDEX
    Explanations

    API documentation and specifications

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

    The neuron fires on technical uppercase terms and acronyms (e.g. API, IMATIC, JSON Schema, Swagger) used in describing or naming API/specification components.

    oai_token-act-pair · o4-miniTriggered 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
     உள
    0.57
     Morn
    0.55
    叛
    0.54
     ergodic
    0.52
     あの
    0.51
     aerobic
    0.51
    horsepower
    0.51
     ইস্ট
    0.50
     winged
    0.50
     马
    0.50
    POSITIVE LOGITS
    Swagger
    1.30
     Swagger
    1.27
    swagger
    1.24
     swagger
    1.10
     api
    1.07
     OpenAPI
    1.07
    openapi
    1.01
    API
    1.00
     API
    0.99
    Api
    0.98
    Activations Density 0.017%

    No Known Activations