© 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. 66655
    Prev
    Next
    INDEX
    Explanations

    game related terms

    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
     thefe
    -1.19
    antart
    -1.16
    gridColumn
    -1.07
    ayant
    -1.02
    плом
    -1.02
    cích
    -1.02
    </h4>
    -1.01
    felves
    -1.01
     Opis
    -1.01
    ウム
    -1.00
    POSITIVE LOGITS
     game
    1.81
     one
    1.36
     games
    1.34
     play
    1.27
     gameplay
    1.21
     start
    1.17
     буде
    1.13
     будете
    1.09
    ड़े
    1.08
    一会儿
    1.07
    Activations Density 0.025%

    No Known Activations