© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21719
    Prev
    Next
    INDEX
    Explanations

    Central Asia and Kazakhstan

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

    The neuron fires strongly on mentions of the country name “Kazakhstan.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    萏
    -2.56
    僦
    -2.33
    鶿
    -2.27
    獴
    -2.14
    麁
    -2.13
    ırl
    -2.11
    铙
    -2.05
    されてる
    -1.98
    祤
    -1.95
    铪
    -1.91
    POSITIVE LOGITS
    s
    2.97
    at
    2.23
    as
    2.22
    需要
    2.17
    蝴
    2.14
     تضيف
    2.13
     membag
    2.09
    一些
    2.08
    ing
    1.99
    k
    1.97
    Activations Density 0.001%

    No Known Activations