© 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. 58752
    Prev
    Next
    INDEX
    Explanations

    developing countries

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

    The neuron activates on the word “developing,” especially in contexts like “developing countries” or “developing world.”

    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
     kredi
    -2.84
     katk
    -2.59
    ৪
    -2.53
     akade
    -2.50
     kanad
    -2.42
     katkı
    -2.38
     klinik
    -2.38
    
    -2.33
    ſu
    -2.25
     votre
    -2.23
    POSITIVE LOGITS
    翾
    2.34
    ﻊ
    2.19
    𞤢
    2.16
     and
    2.13
    ри
    2.11
    檠
    2.11
    晅
    2.09
    鷓
    2.08
    我们在
    2.06
    蚡
    2.05
    Activations Density 0.008%

    No Known Activations