© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21348
    Prev
    Next
    INDEX
    Explanations

    Albania or Albanian cities

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ᙱ
    0.52
     produisent
    0.52
    ामान्य
    0.47
    รัส
    0.47
    ௐ
    0.46
    溼
    0.46
     optimised
    0.46
     ንጥረ
    0.45
     রোগ
    0.45
    :‏
    0.45
    POSITIVE LOGITS
     Albania
    1.45
     Albanian
    1.41
    Alban
    1.23
     Tir
    0.91
     shq
    0.90
     Alban
    0.85
     Kosovo
    0.85
     alb
    0.83
    ë
    0.83
     Alb
    0.75
    Activations Density 0.002%

    No Known Activations