© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75145
    Prev
    Next
    INDEX
    Explanations

    online gaming and multiplayer

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on code and discussion snippets dealing with multiplayer networking—e.g. clients, servers, packets, connections, online players and voice/chat features.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     our
    -1.77
    vensko
    -1.43
    pters
    -1.36
    expiresIn
    -1.35
    }
    -1.29
     nuestro
    -1.23
    digarh
    -1.21
     that
    -1.21
     również
    -1.20
    我们的
    -1.20
    POSITIVE LOGITS
    ibly
    1.20
     gebre
    1.15
     yako
    1.09
    cuz
    1.08
     IMPROV
    1.07
    ferences
    1.06
    Grief
    1.05
    whelmed
    1.04
     feil
    1.02
     ACCIDENT
    1.02
    Activations Density 0.078%

    No Known Activations