© 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. 12478
    Prev
    Next
    INDEX
    Explanations

    Foreign characters and symbols

    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
    el
    1.28
    ோ
    1.23
    所有
    1.13
    이
    1.09
    優れた
    1.05
    Book
    1.02
    rocytes
    0.99
    otemporal
    0.98
    rina
    0.98
     đột
    0.97
    POSITIVE LOGITS
    жён
    1.35
     $(`.
    1.33
     võimalik
    1.30
     ܗܘ
    1.29
     corset
    1.28
    ند
    1.24
    метри
    1.23
    bangan
    1.23
     embossing
    1.22
    ﹙
    1.22
    Activations Density 0.000%

    No Known Activations