© 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-16K
    7. 1155
    Prev
    Next
    INDEX
    Explanations

    shell commands

    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_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
    敬
    0.72
    zimmer
    0.72
     impactful
    0.72
    arium
    0.72
    sembling
    0.70
     Gottes
    0.69
    okol
    0.68
    ach
    0.67
    ill
    0.67
    ophilic
    0.66
    POSITIVE LOGITS
     grep
    1.23
     regexp
    1.19
     文件
    1.15
     命令
    1.14
     删除
    1.14
     {|
    1.12
     arquivos
    1.10
     参数
    1.10
     定义
    1.08
     arquivo
    1.08
    Activations Density 1.393%

    No Known Activations