© 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. 45526
    Prev
    Next
    INDEX
    Explanations

    game service related

    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
    Customers
    -0.88
    锏
    -0.87
    кистан
    -0.84
    sedown
    -0.82
     článku
    -0.81
    Kraj
    -0.80
    Ál
    -0.79
    tistas
    -0.79
    ₃
    -0.78
    マイ
    -0.78
    POSITIVE LOGITS
     player
    1.65
     players
    1.35
     game
    1.20
     PvP
    1.19
    玩家
    1.11
    player
    1.07
     server
    1.05
     Player
    1.03
     jugador
    1.02
     игро
    1.02
    Activations Density 0.010%

    No Known Activations