© 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. 9365
    Prev
    Next
    INDEX
    Explanations

    empathy and compassion

    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
    äv
    0.59
     excitement
    0.58
     উপভোগ
    0.57
    ત્મ
    0.56
    cep
    0.55
     شکایت
    0.55
     vē
    0.54
    嚣
    0.54
     आत्मविश्वास
    0.54
    ɤ
    0.54
    POSITIVE LOGITS
     compassion
    2.28
     compassionate
    2.17
     kindness
    1.90
     empathy
    1.81
     empathetic
    1.79
     pity
    1.71
     sympathy
    1.70
     empath
    1.67
     Kindness
    1.63
    Compass
    1.63
    Activations Density 0.393%

    No Known Activations