© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78524
    Prev
    Next
    INDEX
    Explanations

    roman numerals and historical figures

    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
     Eocene
    -0.85
    kset
    -0.75
     magari
    -0.74
    naires
    -0.71
     Schloss
    -0.71
    seeker
    -0.67
     Capri
    -0.67
    zeni
    -0.66
    ochet
    -0.66
    pheus
    -0.65
    POSITIVE LOGITS
     XIV
    1.00
     fourteenth
    0.98
     Fourteenth
    0.91
     XIII
    0.88
     Dominican
    0.88
     medieval
    0.88
     Medieval
    0.82
     Master
    0.81
     Mongols
    0.80
     Franciscan
    0.79
    Activations Density 0.055%

    No Known Activations