© 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. 955
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on quantified information—numbers, counts, statistics, and other numeric measures (e.g. “millions,” “hundreds,” numeric dates or amounts).

    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
    р
    0.55
    iPad
    0.55
    V
    0.54
    p
    0.54
     ছাত্রী
    0.54
     রুশ
    0.53
    у
    0.53
    Aeonium
    0.52
    v
    0.52
    脘
    0.52
    POSITIVE LOGITS
     Europe
    1.73
    ประเทศไทย
    1.72
     Romania
    1.64
     Poland
    1.63
     বাংলাদেশে
    1.62
     France
    1.61
     Italy
    1.59
     우리나라
    1.59
     India
    1.59
     Spain
    1.58
    Activations Density 2.162%

    No Known Activations