© 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. 24-GEMMASCOPE-2-RES-16K
    4. 6912
    Prev
    Next
    INDEX
    Explanations

    numbered list items

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

    The neuron primarily responds to numeric tokens—especially decimal‐point numbers—detecting quantities or measurements.

    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
    ے
    1.06
    ۷
    1.06
    들에게
    1.05
    ۲
    1.02
    amia
    1.02
    ۳
    1.02
     Sunak
    0.99
    garakan
    0.99
    ことになる
    0.99
    鹉
    0.99
    POSITIVE LOGITS
    ين
    1.12
    らか
    1.03
    ಲ್ಲಿ
    1.00
    گاه
    0.96
    Incoming
    0.96
    пример
    0.96
    т
    0.95
    ت
    0.94
    ંક
    0.93
     glav
    0.93
    Activations Density 6.980%

    No Known Activations