© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73704
    Prev
    Next
    INDEX
    Explanations

    royal and noble titles

    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
     new
    -0.93
     early
    -0.87
    しに
    -0.84
    城主
    -0.82
     many
    -0.81
     whenever
    -0.81
     newly
    -0.80
     possibly
    -0.80
     additional
    -0.79
     Whenever
    -0.79
    POSITIVE LOGITS
     morgan
    1.41
    Pret
    0.87
    quini
    0.86
    鲩
    0.85
     Институ
    0.85
     тик
    0.84
    Scroll
    0.83
     varones
    0.81
    IOT
    0.81
    nelt
    0.81
    Activations Density 0.031%

    No Known Activations