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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 750
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
     숫
    0.79
     консо
    0.76
    Sockets
    0.76
     ছয়
    0.76
    rowCount
    0.75
     trầm
    0.74
    GridLayout
    0.74
     للنساء
    0.74
    빨
    0.72
     تمامی
    0.72
    POSITIVE LOGITS
    某个
    1.52
     item
    1.44
     something
    1.44
     объекта
    1.43
     object
    1.38
     suatu
    1.37
     एखाद्या
    1.36
    事物
    1.36
     organism
    1.30
    某种
    1.29
    Activations Density 5.307%

    No Known Activations