© 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. 10-GEMMASCOPE-RES-131K
    7. 48400
    Prev
    Next
    INDEX
    Explanations

    executive office, power, and agency

    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_10/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
    '
    -2.56
     unſ
    -2.42
     ポーチ
    -2.25
     ſever
    -2.23
     verheir
    -2.17
     ストラップ
    -2.17
    絎
    -2.16
    耵
    -2.14
     remarkably
    -2.13
     墊
    -2.11
    POSITIVE LOGITS
    ୈ
    2.95
    The
    2.41
     sassy
    2.33
    絨
    2.30
     शुर
    2.28
    Лечение
    2.27
    彣
    2.19
     {
    2.11
     постоянно
    2.09
    日前
    2.09
    Activations Density 0.015%

    No Known Activations