© 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. 13415
    Prev
    Next
    INDEX
    Explanations

    willing to do

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

    willingness to spend or accept

    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
     장면
    0.47
     같아요
    0.46
     स्वातंत्र
    0.45
    צ
    0.45
    c
    0.44
     pueblo
    0.43
     같
    0.43
     अभ
    0.43
    താ
    0.43
     থেকেই
    0.42
    POSITIVE LOGITS
     willing
    1.23
    willing
    1.12
     Willing
    1.07
     willingness
    1.04
    愿意
    1.00
    願意
    0.93
     gladly
    0.73
     willingly
    0.72
     accepts
    0.70
     acept
    0.69
    Activations Density 0.090%

    No Known Activations