© 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. 71837
    Prev
    Next
    INDEX
    Explanations

    citizenship, capacitance

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

    The neuron detects words referring to legal national status (e.g., “citizenship,” “nationality,” “naturalisation”).

    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
    </h3>
    -3.23
    鬭
    -2.36
    y
    -2.27
     When
    -2.17
    同じ
    -2.11
    st
    -2.06
    時間
    -2.05
    </em>
    -2.05
     veritable
    -2.05
     dasar
    -2.03
    POSITIVE LOGITS
    </b>
    3.31
    趼
    2.31
    
    2.25
    潆
    2.23
    蹩
    2.19
    </sup>
    2.14
     tarefas
    2.14
     grows
    2.11
     meager
    2.06
     técnico
    2.05
    Activations Density 0.003%

    No Known Activations