© 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. 6062
    Prev
    Next
    INDEX
    Explanations

    marriage, abortion, and reproduction legality

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

    morality and sexuality

    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
     drob
    0.40
     रकम
    0.38
    ยอด
    0.38
    शेखर
    0.38
    成交
    0.38
     दिलचस्प
    0.38
    細
    0.37
    煒
    0.37
     파일을
    0.37
     কলকাতা
    0.37
    POSITIVE LOGITS
     morally
    0.68
     immoral
    0.66
     abortion
    0.62
     Abortion
    0.61
     homosexual
    0.61
     legally
    0.59
    abortion
    0.58
     immor
    0.55
     heterosexual
    0.55
     Parenthood
    0.53
    Activations Density 0.178%

    No Known Activations