© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66106
    Prev
    Next
    INDEX
    Explanations

    simulation 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_34/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
     DAVIS
    -0.84
    Sö
    -0.82
    Liet
    -0.82
    ﻷ
    -0.82
    Infan
    -0.81
     Tü
    -0.79
     Obec
    -0.79
    decide
    -0.79
     rü
    -0.79
     Educación
    -0.79
    POSITIVE LOGITS
     simulation
    1.23
    simulation
    1.20
     simulator
    1.20
     Realistic
    1.16
     realistic
    1.12
     simulate
    1.09
     city
    1.07
     Simulation
    1.05
     simulators
    1.04
    Simulation
    1.01
    Activations Density 0.009%

    No Known Activations