© 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. 4417
    Prev
    Next
    INDEX
    Explanations

    betting odds and trading

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

    The neuron flags generic online platform and service terms (e.g. site, online, account, software, trading, event) commonly found in web-based betting or trading promotions.

    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
     online
    -0.89
    Rn
    -0.86
     Online
    -0.81
    !=-
    -0.77
    眈
    -0.76
    $+$
    -0.76
    WORLD
    -0.76
     vært
    -0.75
    UNGEN
    -0.75
     дорога
    -0.75
    POSITIVE LOGITS
    柢
    0.94
     section
    0.83
     lobby
    0.80
    ₿
    0.79
     DMSO
    0.77
     nhat
    0.77
     gewicht
    0.77
    Preco
    0.75
     conster
    0.75
    Nhan
    0.75
    Activations Density 0.003%

    No Known Activations