© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13677
    Prev
    Next
    INDEX
    Explanations

    exchange or swap

    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
     وق
    0.91
    regression
    0.89
    πά
    0.89
    Brig
    0.87
     Qxh
    0.87
    Aut
    0.86
    diss
    0.83
     た
    0.82
    Marsh
    0.81
    diocese
    0.81
    POSITIVE LOGITS
     exchange
    1.86
     exchanging
    1.84
     exchanges
    1.73
     exchanged
    1.73
    exchange
    1.61
     swapping
    1.50
     intercambio
    1.49
     Exchange
    1.49
     swap
    1.47
     Austausch
    1.45
    Activations Density 0.022%

    No Known Activations