© 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. 59478
    Prev
    Next
    INDEX
    Explanations

    Middle Eastern royal names

    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
    뢰
    -0.77
    ✹
    -0.73
    }_\
    -0.73
    |^{
    -0.73
     skirting
    -0.73
     Spass
    -0.71
    Democratic
    -0.70
    SneakyThrows
    -0.69
     Steine
    -0.69
    φάλ
    -0.69
    POSITIVE LOGITS
     ruler
    1.16
    Ruler
    1.02
     Ruler
    1.02
     Ruling
    1.00
     Crown
    0.94
     rulers
    0.87
     ruling
    0.85
    ruler
    0.82
     Supreme
    0.82
     Sword
    0.80
    Activations Density 0.009%

    No Known Activations