© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99706
    Prev
    Next
    INDEX
    Explanations

    refugees and displaced people

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

    This neuron detects explicit numerical or quantitative expressions (digits, numbers, and large‐scale counts like “millions of refugees”).

    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
     assholes
    -0.83
    ución
    -0.83
    ır
    -0.82
     jerks
    -0.79
     CEOs
    -0.79
    ксу
    -0.76
     diketahui
    -0.75
    斐
    -0.74
     tirs
    -0.73
    ISLAM
    -0.73
    POSITIVE LOGITS
     refugees
    3.89
     refugee
    3.34
    refuge
    2.80
     Refugees
    2.63
     displaced
    2.33
    Refuge
    2.31
     Refugee
    2.14
     evac
    2.08
     refugiados
    1.86
     Flücht
    1.84
    Activations Density 0.077%

    No Known Activations