© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9413
    Prev
    Next
    INDEX
    Explanations

    Ministry of

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

    This neuron detects mentions of government ministries, especially the phrase “Ministry of.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    䊏
    -2.58
     příjem
    -2.58
    庠
    -2.45
     množství
    -2.39
    ඍ
    -2.36
     téměř
    -2.27
    izacji
    -2.22
     velké
    -2.22
     větší
    -2.20
    🆆
    -2.11
    POSITIVE LOGITS
    芣
    3.05
    婓
    2.88
     bús
    2.78
     Répondre
    2.67
    .
    2.55
     Beaucoup
    2.34
    桖
    2.34
     Quels
    2.34
    Когда
    2.30
    Как
    2.28
    Activations Density 0.005%

    No Known Activations