© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77069
    Prev
    Next
    INDEX
    Explanations

    video game consoles and platforms

    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
    northern
    -0.77
     cotidian
    -0.73
    andaag
    -0.73
     vardı
    -0.73
     northern
    -0.72
    negara
    -0.71
    medio
    -0.70
     esenciales
    -0.69
     dimo
    -0.69
     dio
    -0.69
    POSITIVE LOGITS
     console
    4.28
     consoles
    4.00
    console
    3.45
    Console
    3.11
     Console
    3.03
    CONSOLE
    2.33
     consola
    2.27
     consol
    2.08
     kons
    2.00
     Kons
    1.99
    Activations Density 0.052%

    No Known Activations