© 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. 82550
    Prev
    Next
    INDEX
    Explanations

    immigration and ICE

    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
     evacuated
    -0.85
    Inflation
    -0.84
     kväll
    -0.80
     unselfish
    -0.79
     inflationary
    -0.78
    eradish
    -0.78
     aleación
    -0.77
    ulateur
    -0.77
    粼
    -0.77
     Goodman
    -0.75
    POSITIVE LOGITS
     sanctuary
    1.75
     ICE
    1.59
    ICE
    1.49
     immigration
    1.45
     Immigration
    1.42
     Sanctuary
    1.41
    ctuary
    1.30
     undocumented
    1.23
     deportation
    1.10
     immigrants
    1.09
    Activations Density 0.026%

    No Known Activations