© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29900
    Prev
    Next
    INDEX
    Explanations

    loyalty and faithfulness

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

    loyalty and loyal attributes

    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
    t
    0.66
    copter
    0.62
    }=
    0.61
    h
    0.59
    }<
    0.59
    lng
    0.56
    n
    0.55
    v
    0.55
    علي
    0.54
    o
    0.54
    POSITIVE LOGITS
     loyalty
    1.26
     loyal
    1.23
     faithfulness
    1.10
     faithful
    1.02
     fidelity
    1.02
    忠
    1.02
     Loyalty
    1.00
     allegiance
    0.98
    Loy
    0.96
     Loyal
    0.95
    Activations Density 0.058%

    No Known Activations