© 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. 58453
    Prev
    Next
    INDEX
    Explanations

    moral

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

    ethical considerations

    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
    ש
    0.69
    ა
    0.61
    ी
    0.55
    HO
    0.54
    y
    0.54
    ກະ
    0.52
    KE
    0.51
     ম্যানে
    0.51
    ع
    0.50
    he
    0.49
    POSITIVE LOGITS
     Mora
    0.66
     morally
    0.64
     immoral
    0.64
     mor
    0.61
     morals
    0.60
     Morse
    0.59
     MOR
    0.59
     morality
    0.58
     Morales
    0.56
     Moris
    0.55
    Activations Density 0.012%

    No Known Activations