© 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. 34-GEMMASCOPE-RES-131K
    7. 91145
    Prev
    Next
    INDEX
    Explanations

    game modes and stories

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

    The neuron fires on descriptions of a game’s play modes and campaign structure (e.g. “a lengthy single-player campaign … multiplayer modes”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    áct
    -0.79
    ノベーション
    -0.78
     høy
    -0.78
    Ɯ
    -0.78
    ÍTICA
    -0.76
     alkoholu
    -0.74
     opinie
    -0.73
    关键词
    -0.71
    yska
    -0.69
     comune
    -0.68
    POSITIVE LOGITS
     campaign
    2.33
     mode
    2.14
     modes
    1.91
    campaign
    1.85
     Campaign
    1.83
     story
    1.73
    模式
    1.69
    mode
    1.61
     campaigns
    1.60
    Campaign
    1.59
    Activations Density 0.026%

    No Known Activations