© 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. 54361
    Prev
    Next
    INDEX
    Explanations

    prince, count, princess, or 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
    Eliminar
    -0.87
     ।
    -0.78
    unsubscribe
    -0.77
     indicar
    -0.75
     Vorbereitung
    -0.73
     cudd
    -0.72
    ConstraintMaker
    -0.72
     Size
    -0.72
    タップ
    -0.70
    $^{-
    -0.70
    POSITIVE LOGITS
    ザイン
    0.91
    Counts
    0.91
     morgan
    0.91
     Wittgenstein
    0.88
     Counts
    0.85
    伯爵
    0.85
     Count
    0.85
    Prince
    0.84
     count
    0.83
     кня
    0.80
    Activations Density 0.056%

    No Known Activations