© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2081
    Prev
    Next
    INDEX
    Explanations

    romance, relationships, and pregnancy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ۔
    0.62
    ה
    0.55
    是
    0.42
    G
    0.41
    գ
    0.41
    માં
    0.40
    ți
    0.38
    는
    0.38
    يا
    0.38
    மாக
    0.37
    POSITIVE LOGITS
     Pregnancy
    0.59
     Marriage
    0.57
     Sexual
    0.49
     Abortion
    0.49
    ↵
    0.48
     Maternity
    0.46
     Reproductive
    0.46
     Authorization
    0.44
     Maternal
    0.44
     Parenthood
    0.44
    Activations Density 0.585%

    No Known Activations