© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12013
    Prev
    Next
    INDEX
    Explanations

    shopping, payment, refunds, and seller reputation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
     socially
    0.84
     culturally
    0.81
     historically
    0.78
     alongside
    0.78
     Jones
    0.75
     –
    0.73
     encompassing
    0.72
     overarching
    0.71
     recurring
    0.70
     stands
    0.70
    POSITIVE LOGITS
     товаров
    1.75
     aliexpress
    1.71
    店铺
    1.69
     Aliexpress
    1.58
     товары
    1.52
     negozio
    1.49
     товара
    1.48
     compradores
    1.45
     店
    1.40
    ！！！
    1.40
    Activations Density 0.005%

    No Known Activations