© 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. 91783
    Prev
    Next
    INDEX
    Explanations

    internment camps and related histories

    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
    槇
    -0.83
    石川
    -0.82
    塙
    -0.82
    韮
    -0.80
     滝
    -0.79
    рный
    -0.78
     Chara
    -0.78
    TypeDef
    -0.75
     Ра
    -0.75
     Barnabas
    -0.73
    POSITIVE LOGITS
     intern
    1.09
     Manzan
    1.06
     interne
    0.93
     redress
    0.88
     relocation
    0.85
     Intern
    0.84
     fishing
    0.82
     Relocation
    0.81
     farming
    0.80
     camps
    0.77
    Activations Density 0.031%

    No Known Activations