Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7750
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    gg-gs/gemma-scope-2-4b-it/resid_post
    Prompts (Dashboard)
    273,612 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ر
    2.58
    ight
    2.54
    и
    2.47
    estomac
    2.47
     deter
    2.46
    tschaft
    2.46
     attent
    2.44
    arie
    2.43
    ான
    2.43
    과
    2.43
    POSITIVE LOGITS
     macam
    2.83
     불구하고
    2.76
    𝖙
    2.61
    लिये
    2.58
    ை
    2.56
    которые
    2.51
    лення
    2.48
    ယာ
    2.48
    ویت
    2.48
     refrained
    2.48
    Activations Density 0.020%

    No Known Activations