© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9336
    Prev
    Next
    INDEX
    Explanations

    courage and bravery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     workmanship
    0.58
     reminders
    0.52
    フー
    0.51
    ጣ
    0.51
    jalanan
    0.50
    obenzene
    0.50
     multiplying
    0.50
    HNO
    0.49
     कमा
    0.49
     preventable
    0.49
    POSITIVE LOGITS
     courage
    2.41
     brave
    2.25
     bravery
    2.17
     boldness
    2.17
     courageous
    2.14
     daring
    2.13
     bold
    2.00
     bravely
    2.00
    勇
    1.95
     boldly
    1.93
    Activations Density 0.295%

    No Known Activations