© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 13194
    Prev
    Next
    INDEX
    Explanations

    death and suicide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_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
     Crimes
    1.23
     psychiat
    1.20
    ל
    1.19
     wrongdoing
    1.18
     DAI
    1.16
     DAT
    1.10
     narc
    1.09
     paga
    1.09
    ل
    1.07
     kidn
    1.05
    POSITIVE LOGITS
    elling
    1.19
    提高
    1.18
    ㌔
    1.17
     అంశ
    1.14
    ých
    1.13
    ets
    1.11
     või
    1.10
    elf
    1.09
    mäßig
    1.09
    ão
    1.09
    Activations Density 0.129%

    No Known Activations