© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9553
    Prev
    Next
    INDEX
    Explanations

    asylum seekers and refugees

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

    immigration and migration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dieting
    0.44
    促销
    0.43
     மஞ்ச
    0.43
    痿
    0.42
    歆
    0.41
     Endocrinology
    0.41
    缠
    0.40
     प्रमो
    0.40
    掉
    0.40
     glands
    0.40
    POSITIVE LOGITS
     refugee
    2.55
     Refugee
    2.44
     refugees
    2.34
     Refugees
    2.28
     asylum
    2.03
     Flücht
    2.03
     শরণার্থী
    2.00
     migrants
    1.95
     UNHCR
    1.94
     refugi
    1.91
    Activations Density 0.230%

    No Known Activations