© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129073
    Prev
    Next
    INDEX
    Explanations

    foreign language text examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     aval
    0.48
     acar
    0.46
     fandom
    0.44
     capace
    0.44
     escog
    0.44
     ライン
    0.43
     APP
    0.43
     fiz
    0.43
     vang
    0.42
    >>,
    0.42
    POSITIVE LOGITS
     सूचना
    0.48
    ického
    0.46
     పుస్త
    0.45
    एं
    0.45
    เริ่ม
    0.45
    від
    0.44
     शुरूआत
    0.44
     गोयल
    0.44
     मित्त
    0.43
     पुस्तकों
    0.43
    Activations Density 0.002%

    No Known Activations