© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110510
    Prev
    Next
    INDEX
    Explanations

    Europe and migrants

    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
     Slu
    -0.75
     Zand
    -0.74
     revan
    -0.73
    Zé
    -0.73
    жены
    -0.73
    ጊ
    -0.73
     pof
    -0.72
     Spes
    -0.71
    uestos
    -0.71
     armen
    -0.70
    POSITIVE LOGITS
     migrant
    1.43
     migrants
    1.30
     migration
    1.08
    mig
    1.02
     Libya
    1.02
     Europe
    1.01
     Libyan
    0.96
     Migrant
    0.94
     Mig
    0.94
    Mig
    0.93
    Activations Density 0.017%

    No Known Activations