© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12361
    Prev
    Next
    INDEX
    Explanations

    hints for context

    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
    Negative Logits
    lar
    3.14
     quenched
    3.00
    ে
    2.95
    هایی
    2.93
    ه
    2.62
    o
    2.57
    daki
    2.54
    مة
    2.52
    مع
    2.50
    يا
    2.50
    POSITIVE LOGITS
    𝑒
    3.64
    ни
    3.27
    ния
    3.22
    𝑎
    3.16
    𝑈
    3.13
    𝑀
    3.08
    ت
    3.06
    𝐿
    3.04
    𝑟
    3.02
    𝑔
    2.96
    Activations Density 0.016%

    No Known Activations