© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6185
    Prev
    Next
    INDEX
    Explanations

    exchange and payment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    एं
    0.47
     கட்டமை
    0.46
     tendencias
    0.44
     categorías
    0.43
     Zeit
    0.43
     активности
    0.43
    层
    0.43
    酶
    0.43
    kości
    0.42
     interactive
    0.42
    POSITIVE LOGITS
     বিনিম
    0.99
     reward
    0.98
    交換
    0.98
     exchange
    0.96
     payment
    0.91
     обмен
    0.90
     échange
    0.90
    exchange
    0.89
     exchanged
    0.89
     exchanging
    0.86
    Activations Density 0.141%

    No Known Activations