© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206663
    Prev
    Next
    INDEX
    Explanations

    your family condolences

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

    sympathy for family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Decedent
    0.53
     deceased
    0.52
    deceased
    0.50
    去世
    0.49
    deaths
    0.48
     இறந்த
    0.46
    逝
    0.46
    諡
    0.45
     शोक
    0.44
    memorial
    0.44
    POSITIVE LOGITS
     Finlandia
    0.46
     agri
    0.43
     Alb
    0.43
     And
    0.42
     Gig
    0.42
     errorMessage
    0.42
     Library
    0.41
     Ore
    0.41
     Blink
    0.41
     Kona
    0.41
    Activations Density 0.012%

    No Known Activations