© 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. 34-GEMMASCOPE-RES-131K
    7. 83034
    Prev
    Next
    INDEX
    Explanations

    refugees fleeing persecution

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

    The neuron strongly activates on refugee- and asylum-related terms and phrases (e.g. asylum, seekers, refugees, UNHCR, unaccompanied children, protections).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    有助
    -0.84
    MSG
    -0.81
     ود
    -0.77
     Anadolu
    -0.76
     leerlingen
    -0.74
     codigo
    -0.74
    Tja
    -0.72
     aang
    -0.71
    ścic
    -0.71
     dvs
    -0.71
    POSITIVE LOGITS
     fear
    1.36
     UNHCR
    1.26
     feared
    1.16
     persecution
    1.15
    fear
    1.12
     fearing
    1.09
     fears
    1.09
    Fear
    1.05
     sợ
    1.05
     Refugee
    1.01
    Activations Density 0.010%

    No Known Activations