© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2413
    Prev
    Next
    INDEX
    Explanations

    "Large Model Systems Organization"

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

    The neuron flags capitalized names—especially proper nouns denoting companies, places, or other named entities.

    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_24_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
     जोकि
    0.50
     gimm
    0.49
    你也
    0.46
    你
    0.46
     and
    0.46
    偷偷
    0.46
    ighty
    0.45
    াবেন
    0.45
     shamb
    0.45
    啦
    0.43
    POSITIVE LOGITS
     オレンジ
    0.54
     ク
    0.50
     ウ
    0.50
     学習
    0.47
     ソ
    0.47
     ด
    0.46
     ৰ
    0.46
    ovjek
    0.46
     ヘア
    0.46
     取り
    0.45
    Activations Density 0.144%

    No Known Activations