© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12158
    Prev
    Next
    INDEX
    Explanations

    Appendix A

    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_9_width_262k_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
    橥
    2.31
    Dengan
    2.02
    ਾਨ
    1.98
    Logged
    1.95
     Yhat
    1.92
    س
    1.90
     Seorang
    1.90
     Bxe
    1.86
    Hoje
    1.86
     Dietrich
    1.84
    POSITIVE LOGITS
    깐
    2.32
    та
    2.21
    те
    2.06
    ্ক
    1.91
    다
    1.89
    nobyl
    1.89
    ные
    1.85
    турой
    1.84
     haunt
    1.82
    maid
    1.82
    Activations Density 0.003%

    No Known Activations