© 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. 8346
    Prev
    Next
    INDEX
    Explanations

    ed, 2nd, 3rd

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

    The main thing this neuron does is spot numeric bibliographic details (e.g. page numbers, publication years, measurements, and other numeric identifiers).

    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
     DOI
    0.63
    τσ
    0.57
     Pais
    0.52
     রিভিউ
    0.52
     STAY
    0.51
    묵
    0.51
     રહેશે
    0.51
     Maj
    0.50
     Tag
    0.49
     JPG
    0.48
    POSITIVE LOGITS
    Includes
    0.70
     Includes
    0.65
     namely
    0.61
    orec
    0.61
     includes
    0.60
     ,[
    0.60
     अधिवक्ता
    0.59
    ",[
    0.59
     Namely
    0.59
    Rite
    0.59
    Activations Density 0.051%

    No Known Activations