© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143636
    Prev
    Next
    INDEX
    Explanations

    internalized homophobia, marriage, citizenship

    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_31_width_262k_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
    .
    0.47
     sandpaper
    0.46
     Cosmetics
    0.42
     détermin
    0.41
     looking
    0.41
     Ladies
    0.41
     verità
    0.40
    ،
    0.40
     dyes
    0.40
     Coloring
    0.40
    POSITIVE LOGITS
     ਤਾਂ
    0.54
     пе
    0.48
     ಎರಡು
    0.48
    нув
    0.47
    頜
    0.44
    allocate
    0.43
    <unused675>
    0.43
     са
    0.43
    fuel
    0.42
     ಅವಕಾಶ
    0.42
    Activations Density 0.007%

    No Known Activations