© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48595
    Prev
    Next
    INDEX
    Explanations

    death and pronouns

    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
    Negative Logits
     faux
    0.41
     currently
    0.40
     सध्या
    0.38
    目前
    0.37
    अगर
    0.37
     ఇప్పటికే
    0.37
     printable
    0.37
     உள்ளனர்
    0.37
    滿
    0.37
    当前
    0.36
    POSITIVE LOGITS
     posthum
    1.34
     died
    1.30
     murió
    1.20
     morreu
    1.19
     døde
    1.16
     meninggal
    1.11
     사망
    1.11
     умер
    1.10
     morrer
    1.08
     deceduto
    1.08
    Activations Density 0.038%

    No Known Activations