© 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. 13802
    Prev
    Next
    INDEX
    Explanations

    search and related queries

    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
     lectured
    0.67
    骶
    0.64
    糕
    0.63
     Herd
    0.62
     Mortara
    0.61
     মিটার
    0.60
    Invalids
    0.60
    轧
    0.60
    bonding
    0.60
    臀
    0.59
    POSITIVE LOGITS
     search
    3.75
    搜索
    3.53
    Search
    3.48
     Search
    3.46
     searches
    3.45
    search
    3.41
     검색
    3.35
    検索
    3.22
     searching
    3.13
     Searches
    3.12
    Activations Density 0.654%

    No Known Activations