© 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. 77138
    Prev
    Next
    INDEX
    Explanations

    Barack Obama

    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
    sterreich
    -0.80
    tice
    -0.78
    INDUSTRY
    -0.78
    最快更新
    -0.77
    IZA
    -0.75
     Nikola
    -0.73
    cese
    -0.73
    𝔲
    -0.73
    intah
    -0.73
     libertarian
    -0.72
    POSITIVE LOGITS
     Barack
    1.49
     Obama
    1.47
     Kenyan
    1.32
     Michelle
    1.26
     Kenya
    1.24
    Obama
    1.16
     michelle
    1.16
     Chicago
    1.11
    Michelle
    1.07
     Hawaii
    1.05
    Activations Density 0.049%

    No Known Activations