© 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-65K
    7. 5646
    Prev
    Next
    INDEX
    Explanations

    Sudan and nationalities

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Velvet
    0.43
     Baths
    0.43
     Underground
    0.42
     Chilean
    0.42
    ปฏิ
    0.42
     فرش
    0.42
     Tamil
    0.41
     chile
    0.41
    恽
    0.41
     subter
    0.41
    POSITIVE LOGITS
     Ugandan
    0.59
     Sudanese
    0.59
     Sudan
    0.58
     Kampala
    0.53
     Uganda
    0.51
     Khartoum
    0.44
     السود
    0.42
    BCL
    0.42
    JOSE
    0.42
    Ug
    0.40
    Activations Density 0.025%

    No Known Activations