© 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. 12282
    Prev
    Next
    INDEX
    Explanations

    multi-language words

    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
     που
    1.42
     ไม่
    1.38
     thwarted
    1.37
     yanlı
    1.30
     daimyo
    1.28
     minded
    1.27
     уйнарга
    1.26
     glial
    1.26
    🆈
    1.25
    endtime
    1.24
    POSITIVE LOGITS
     Szcz
    1.18
    ा
    1.18
    <0x9A>
    1.17
     respectiv
    1.17
    然后
    1.16
     moze
    1.15
    ्हा
    1.15
     beschikbaar
    1.14
    <0xBD>
    1.12
    yn
    1.12
    Activations Density 0.064%

    No Known Activations