© 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. 22423
    Prev
    Next
    INDEX
    Explanations

    Azerbaijan, Jennie, Gentile, confectionery

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

    The neuron strongly activates on occurrences of the country name “Azerbaijan” (and close variants) in the text.

    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
    at
    -3.58
    as
    -3.22
    ↵↵
    -3.14
    x
    -2.86
    y
    -2.78
    we
    -2.75
    因为他
    -2.70
    矇
    -2.67
    li
    -2.56
    ET
    -2.56
    POSITIVE LOGITS
    магазин
    3.03
    
    2.67
     शुर
    2.59
    เกง
    2.52
    鳚
    2.50
    ``
    2.48
    锕
    2.41
    ꪔ
    2.36
    ～～～
    2.31
    芣
    2.31
    Activations Density 0.014%

    No Known Activations