© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10218
    Prev
    Next
    INDEX
    Explanations

    economics

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

    The neuron activates on numeric tokens (years, volume/page numbers, and other digits) as they appear in reference/citation entries.

    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
     quốc
    0.67
     국가
    0.66
     thermodynam
    0.65
     manifestly
    0.64
     $<\
    0.61
     hydrocarbon
    0.61
     diminution
    0.61
     magnitud
    0.61
     $\
    0.60
     differentially
    0.60
    POSITIVE LOGITS
    Foundation
    0.64
    awie
    0.63
     neuest
    0.61
     Rankings
    0.60
    Naming
    0.60
    wayne
    0.58
     Foundation
    0.57
    Female
    0.57
     Surveys
    0.56
    Erik
    0.56
    Activations Density 0.036%

    No Known Activations