© 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. 22-GEMMASCOPE-RES-131K
    7. 13791
    Prev
    Next
    INDEX
    Explanations

    competed in Olympics/Games

    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_22/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
     while
    -1.27
     it
    -1.22
    龛
    -1.20
     new
    -1.19
     if
    -1.14
    лә
    -1.06
    offers
    -1.05
     offer
    -1.05
     кнопки
    -1.05
     its
    -1.04
    POSITIVE LOGITS
     national
    1.45
     training
    1.42
     национа
    1.38
     трени
    1.36
     Thương
    1.35
     kompeti
    1.34
    ussia
    1.30
     equipamento
    1.27
    ейчас
    1.27
    stüt
    1.26
    Activations Density 0.155%

    No Known Activations