© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63080
    Prev
    Next
    INDEX
    Explanations

    players in 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
     Jé
    -1.01
    ™
    -0.98
    IOUtils
    -0.94
     સ
    -0.93
    rijf
    -0.91
    employee
    -0.91
    worker
    -0.91
    engers
    -0.91
    ncia
    -0.90
    jska
    -0.90
    POSITIVE LOGITS
     teammates
    1.32
     team
    1.32
     deaths
    1.25
     teammate
    1.16
     players
    1.14
     matchmaking
    1.13
     solo
    1.13
     player
    1.12
     playing
    1.05
     losing
    1.04
    Activations Density 0.028%

    No Known Activations