© 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. 34-GEMMASCOPE-RES-131K
    7. 62510
    Prev
    Next
    INDEX
    Explanations

    Sims and SimCity

    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
    Negative Logits
    本番
    -0.68
    Schloss
    -0.68
     Schloss
    -0.65
    extensive
    -0.65
    trx
    -0.65
    Homemade
    -0.65
     nombrado
    -0.64
    Materiale
    -0.64
    Animations
    -0.63
    خاذ
    -0.63
    POSITIVE LOGITS
     Sims
    1.57
     sim
    1.44
     sims
    1.41
    Sim
    1.37
     Sim
    1.34
    SIM
    1.28
    Sims
    1.26
    sim
    1.22
    sims
    1.16
     SIM
    1.13
    Activations Density 0.035%

    No Known Activations