© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12919
    Prev
    Next
    INDEX
    Explanations

    geopolitical

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     landlab
    0.47
     صاحب
    0.45
     zaměst
    0.43
     восстанов
    0.43
     Стаўкі
    0.42
    LLS
    0.42
    ญาต
    0.42
     ਕਰ
    0.41
     বন
    0.41
    湖
    0.41
    POSITIVE LOGITS
     myBuilder
    0.42
     Cavalry
    0.42
     Prado
    0.40
    -]+
    0.40
     Mic
    0.39
     Kai
    0.39
     croix
    0.38
     PDK
    0.38
     Arm
    0.37
     Syria
    0.37
    Activations Density 0.000%

    No Known Activations