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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 8399
    Prev
    Next
    INDEX
    Explanations

    grief and sadness

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

    Text about grief, bereavement, and offering comfort or emotional support (including condolences and resources for coping).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     wacky
    0.49
    面白い
    0.47
    😎
    0.47
     exciting
    0.46
    สนุก
    0.46
     adventure
    0.46
     Adventure
    0.45
     😎
    0.45
    楽しい
    0.44
    好奇
    0.44
    POSITIVE LOGITS
     grief
    2.19
     sorrow
    2.09
     sadness
    2.03
     grieving
    1.98
     heartbroken
    1.94
     heartbreak
    1.92
     grieve
    1.92
     Grief
    1.83
     heartbreaking
    1.82
     mourn
    1.80
    Activations Density 0.060%

    No Known Activations