© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 251306
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly when the text mentions the video game Disco Elysium (tokens from the game's title or related references).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stej
    0.55
    ++]
    0.50
     commend
    0.48
     Над
    0.47
     Zeng
    0.46
     gør
    0.46
     и
    0.45
     كرد
    0.45
     conseil
    0.45
     laud
    0.44
    POSITIVE LOGITS
    izumab
    0.47
    只会
    0.47
    entery
    0.46
    macos
    0.44
    severity
    0.43
    βολ
    0.43
    事件
    0.42
    南
    0.42
    搜索
    0.42
    cimentos
    0.42
    Activations Density 0.010%

    No Known Activations