© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 4181
    Prev
    Next
    INDEX
    Explanations

    Reinforcement Learning from Human Feedback

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    AndDelete
    1.43
     그런데
    1.38
    したが
    1.36
    하지만
    1.35
     واذا
    1.35
    ,|
    1.35
    而且
    1.34
     setShow
    1.31
     وتح
    1.30
     &&
    1.30
    POSITIVE LOGITS
     celebrates
    1.21
     iconic
    1.20
    ก็
    1.18
     celebrating
    1.17
    kun
    1.14
     breathtaking
    1.13
    tracker
    1.12
    बानी
    1.11
     featuring
    1.10
     Whitehall
    1.10
    Activations Density 0.552%

    No Known Activations