© 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. 2253
    Prev
    Next
    INDEX
    Explanations

    in-game context or setting

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

    The neuron fires on numeric references—counts, measurements, or quantities (e.g. numbers, amounts, and related quantifiers).

    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
     seti
    -0.77
     URB
    -0.77
    ocuk
    -0.76
     Solved
    -0.76
     nack
    -0.74
     pikachu
    -0.73
    infty
    -0.73
     yuri
    -0.73
    dell
    -0.73
     людини
    -0.73
    POSITIVE LOGITS
     ingame
    4.03
     game
    2.88
    ゲーム
    2.34
    game
    2.14
    游戏
    2.05
     in
    2.00
     внутри
    1.96
    遊戲
    1.88
     gameplay
    1.82
     игро
    1.79
    Activations Density 0.052%

    No Known Activations