© 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. 10-GEMMASCOPE-RES-131K
    7. 8947
    Prev
    Next
    INDEX
    Explanations

    Xbox consoles and products

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

    This neuron fires on mentions of the Xbox gaming platform (e.g. “Xbox One,” “Xbox 360,” etc.).

    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
    瑨
    -2.80
    </sup>
    -2.64
     This
    -2.48
    '
    -2.36
    </h4>
    -2.34
     That
    -2.33
    聼
    -2.30
     With
    -2.27
    のお店
    -2.20
    豨
    -2.19
    POSITIVE LOGITS
     {
    2.69
    Según
    2.39
     tens
    2.27
    苹
    2.25
    ᠂
    2.16
    𓋼
    2.16
     "}
    2.14
    te
    2.13
    蹰
    2.09
    alakip
    2.08
    Activations Density 0.002%

    No Known Activations