© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 551
    Prev
    Next
    INDEX
    Explanations

    in-game items and customization

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

    The neuron fires on mentions of in-game cosmetic items or downloadable content (e.g. skins, music kits, gifts).

    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
    Демографія
    -0.82
    öscht
    -0.74
     Independiente
    -0.74
     Evita
    -0.74
    retval
    -0.71
     joc
    -0.70
     onsite
    -0.70
    dims
    -0.69
     ನಿ
    -0.69
    Genre
    -0.68
    POSITIVE LOGITS
     skin
    2.94
     skins
    2.72
    skin
    2.17
    skins
    2.03
    Skin
    1.98
     Skin
    1.95
    皮肤
    1.94
     cosmetic
    1.91
     cosmetics
    1.91
     Skins
    1.79
    Activations Density 0.011%

    No Known Activations