© 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. 8437
    Prev
    Next
    INDEX
    Explanations

    comma

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

    The neuron selectively activates on named-entity tokens—proper names, dates, numbers, and other specific entity mentions.

    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
    etc
    0.74
     &
    0.73
     etc
    0.65
     copyspace
    0.64
    してます
    0.59
    গণ
    0.58
     लेकर
    0.57
     তৈরী
    0.57
     सुद्धा
    0.57
    してた
    0.57
    POSITIVE LOGITS
    ،
    2.78
    ,
    2.52
    ፣
    2.39
    ，
    2.38
    ၊
    2.30
     ،
    1.97
    ‌,
    1.88
    ,//
    1.86
    $,
    1.81
     ፣
    1.80
    Activations Density 1.795%

    No Known Activations