© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1425
    Prev
    Next
    INDEX
    Explanations

    government offices and roles

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

    The neuron detects mentions of formal organizational or governmental office titles (e.g., “Office,” “Directorate,” “Ministry of…,” “Presidency”).

    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
    2
    -1.50
    </em>
    -1.42
    !"
    -1.37
    "",
    
    -1.37
    ご注意
    -1.34
     или
    -1.27
    "
    -1.27
    Then
    -1.26
    Instead
    -1.25
    僅
    -1.25
    POSITIVE LOGITS
     it
    1.50
    𝗞
    1.34
    Jährige
    1.34
     of
    1.28
     sencillas
    1.27
     inalámb
    1.27
     таких
    1.20
    起来的
    1.19
    层的
    1.16
    Dagger
    1.16
    Activations Density 0.043%

    No Known Activations