© 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. 10599
    Prev
    Next
    INDEX
    Explanations

    Tanzania

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

    The neuron fires on fragments containing the character sequence “kaz,” as in proper‐name or high‐activation tokens like “Kaz” or “kazakh.”

    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
    Hotkey
    0.73
    jetbrains
    0.64
     Peachtree
    0.61
    ServletException
    0.58
    Isometric
    0.57
    KSpriteNode
    0.56
    சென்னை
    0.55
    ೖ
    0.55
    पत्र
    0.55
    Atlanta
    0.54
    POSITIVE LOGITS
     wx
    1.47
    wx
    1.37
    Wx
    1.01
    微信
    0.99
    小程序
    0.93
    WX
    0.86
     Tanz
    0.84
    weapp
    0.81
     Tanzania
    0.78
     WeChat
    0.77
    Activations Density 0.034%

    No Known Activations