© 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. 91464
    Prev
    Next
    INDEX
    Explanations

    Mitt Romney

    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
     borough
    -0.85
    ashimi
    -0.84
     lager
    -0.81
    rítica
    -0.80
     Conti
    -0.75
    วง
    -0.75
     unic
    -0.74
    írus
    -0.74
     Stalin
    -0.73
     pras
    -0.73
    POSITIVE LOGITS
     Romney
    1.47
     Bain
    1.41
     Mitt
    1.35
    Rom
    1.23
    Mitt
    1.22
    Bain
    1.09
     комнате
    0.82
     Mormon
    0.82
     Massachusetts
    0.81
     mitt
    0.79
    Activations Density 0.033%

    No Known Activations