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. 7595
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post
    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
    ल
    3.71
    ה
    3.29
    
    3.02
    deki
    2.95
    nd
    2.74
    ndan
    2.62
    
    2.61
    Золо
    2.57
    দ
    2.54
    พย์
    2.52
    POSITIVE LOGITS
    到的
    2.81
    THUR
    2.75
    শীল
    2.65
    efeller
    2.63
     пищи
    2.54
     antlers
    2.53
    rishna
    2.53
    hline
    2.50
    ৩
    2.50
    SIB
    2.49
    Activations Density 0.023%

    No Known Activations