© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94497
    Prev
    Next
    INDEX
    Explanations

    died aged

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

    obituaries and passing away

    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
     fuelwood
    0.48
     scarring
    0.44
     vasocon
    0.43
     앉
    0.42
     fuel
    0.41
     welding
    0.40
     oxidizing
    0.40
     hibernate
    0.40
     exfoliating
    0.40
     caffeine
    0.39
    POSITIVE LOGITS
    訃
    0.85
     tributes
    0.82
     décadas
    0.81
     obituary
    0.80
     श्रद्धांजलि
    0.77
     निधन
    0.77
     Obituary
    0.75
     falleció
    0.73
     condolences
    0.70
     शोक
    0.70
    Activations Density 0.134%

    No Known Activations