© 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. 1000
    Prev
    Next
    INDEX
    Explanations

    mortgage calculators, bomb threats

    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
    ↵↵
    1.03
    **
    0.98
     **
    0.84
    ↵
    0.80
    **(
    0.76
    *
    0.74
    ${
    0.70
        
    0.70
    <b>
    0.67
    com
    0.66
    POSITIVE LOGITS
     Overview
    1.57
     Facts
    1.48
     FAQs
    1.48
     Cómo
    1.42
     Glossary
    1.41
     FAQ
    1.39
     Bibliography
    1.37
     Basics
    1.36
     Myths
    1.31
     overview
    1.30
    Activations Density 0.367%

    No Known Activations