© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7888
    Prev
    Next
    INDEX
    Explanations

    age

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

    The neuron strongly activates on legal or regulatory references—e.g. statute names, section numbers, and formal compliance citations.

    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
     किसान
    0.52
    园
    0.50
    景
    0.50
     пайда
    0.46
    观
    0.46
     stoichi
    0.46
    GUID
    0.45
    栅
    0.45
    সঙ্ঘ
    0.45
     SEO
    0.45
    POSITIVE LOGITS
     age
    3.77
    年龄
    3.50
    年齢
    3.36
     edad
    3.33
     Age
    3.27
     aged
    3.25
    Age
    3.08
     ages
    3.02
     usia
    3.00
     âge
    2.98
    Activations Density 0.995%

    No Known Activations