© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45694
    Prev
    Next
    INDEX
    Explanations

    mentions of 'game'

    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
    Negative Logits
     on
    -2.45
     for
    -2.16
     with
    -1.83
     an
    -1.78
     all
    -1.77
     or
    -1.73
     under
    -1.70
     in
    -1.69
     from
    -1.68
     after
    -1.67
    POSITIVE LOGITS
    ⎔
    2.02
    皷
    2.02
     Atención
    1.96
     Infór
    1.88
     Dinas
    1.71
    roughly
    1.70
     fiscale
    1.69
     gebracht
    1.68
     siè
    1.66
    referred
    1.66
    Activations Density 0.023%

    No Known Activations