© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8463
    Prev
    Next
    INDEX
    Explanations

    giving and compassion

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

    kindness and altruism

    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_40_width_16k_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
    汇报
    0.45
    兴奋
    0.43
     आरो
    0.43
    納得
    0.41
    郢
    0.41
     विद्रोह
    0.40
     اعتماد
    0.39
    骜
    0.39
     تحد
    0.38
     धूम
    0.38
    POSITIVE LOGITS
     generosity
    1.87
     kindness
    1.76
     altru
    1.61
     compassion
    1.58
     compassionate
    1.50
     Kindness
    1.50
     selfless
    1.49
     benevolence
    1.45
     generous
    1.41
     charitable
    1.39
    Activations Density 0.577%

    No Known Activations