© 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. 34-GEMMASCOPE-RES-131K
    4. 115952
    Prev
    Next
    INDEX
    Explanations

    illegal and undocumented immigrants

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     thụ
    -0.89
    竊
    -0.85
     десер
    -0.71
     appara
    -0.71
    westen
    -0.69
    urato
    -0.69
    ader
    -0.69
     powst
    -0.68
    ceous
    -0.68
    Indoor
    -0.68
    POSITIVE LOGITS
     immigrant
    3.58
     immigrants
    3.56
     migrant
    3.13
     foreign
    3.03
     migrants
    2.84
     foreigners
    2.81
    immig
    2.80
     foreigner
    2.75
     alien
    2.42
     aliens
    2.39
    Activations Density 0.067%

    No Known Activations