© 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. 2366
    Prev
    Next
    INDEX
    Explanations

    Korean language translation

    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
    redu
    0.36
     மருத்துவ
    0.34
    _{
    0.33
     கடுமையான
    0.33
    ỷ
    0.33
    um
    0.32
     restricts
    0.32
     festgestellt
    0.32
    were
    0.32
     ถ
    0.32
    POSITIVE LOGITS
     একটু
    0.43
     magari
    0.38
     choisi
    0.38
     pueda
    0.38
     possa
    0.38
     cheeky
    0.38
     prowess
    0.37
     okazji
    0.37
     digamos
    0.37
     comodidad
    0.36
    Activations Density 0.117%

    No Known Activations