© 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. 31-GEMMASCOPE-2-RES-16K
    4. 553
    Prev
    Next
    INDEX
    Explanations

    Bay Area

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

    This neuron detects named-entity tokens, i.e. proper names of people, places, organizations, and similar 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_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
     উহা
    0.38
    せる
    0.36
    นั้น
    0.34
    euler
    0.33
    ubit
    0.33
    ㄝ
    0.33
    上記の
    0.33
    żeń
    0.33
     ইহা
    0.32
    ставля
    0.32
    POSITIVE LOGITS
     ­
    0.45
     ‎
    0.45
     nationale
    0.42
     outra
    0.40
     statunitense
    0.40
     alleges
    0.39
     lamented
    0.39
     national
    0.38
     ravaged
    0.38
     estadounidense
    0.38
    Activations Density 3.366%

    No Known Activations