© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117670
    Prev
    Next
    INDEX
    Explanations

    courage and bravery

    np_acts-logits-general · gemini-2.5-flash-lite

    courage to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    u
    0.94
    xious
    0.64
    т
    0.62
    וס
    0.59
     организма
    0.59
    밭
    0.59
    늪
    0.58
     Tekh
    0.58
    on
    0.57
    지가
    0.55
    POSITIVE LOGITS
     courageous
    1.01
     dared
    0.89
     brave
    0.88
     daring
    0.87
     bravely
    0.86
     boldly
    0.84
    敢
    0.77
     audacious
    0.73
     bold
    0.73
     bravery
    0.73
    Activations Density 0.049%

    No Known Activations