© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8217
    Prev
    Next
    INDEX
    Explanations

    pagination and page numbers

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

    This neuron activates on forum navigation and pagination elements—things like page numbers, thread indexes, section links, and other UI/navigation tokens.

    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
     Lax
    0.64
     collections
    0.61
    CodeableConcept
    0.60
     COLLECTION
    0.57
    æn
    0.55
    MongoClient
    0.55
    Obj
    0.55
    HCC
    0.54
    コレクション
    0.54
    ClN
    0.53
    POSITIVE LOGITS
     pagina
    0.61
    льга
    0.59
     страница
    0.59
     page
    0.58
     go
    0.57
     isolating
    0.57
     navigating
    0.56
     página
    0.54
     по
    0.54
     راس
    0.54
    Activations Density 0.006%

    No Known Activations