© 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. 181222
    Prev
    Next
    INDEX
    Explanations

    death and survival events

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

    surviving or outliving others

    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
     Pali
    0.41
    丰富的
    0.39
     건설
    0.39
    न्दावन
    0.39
     సమావేశ
    0.37
     தண்ணீர்
    0.37
     регули
    0.36
    화
    0.36
    擠
    0.35
    sulph
    0.35
    POSITIVE LOGITS
     predeceased
    0.98
     prede
    0.64
     deaths
    0.62
     precede
    0.61
     precedes
    0.55
     died
    0.53
     survived
    0.53
     sobreviv
    0.52
     মৃত্যু
    0.50
     survive
    0.50
    Activations Density 0.035%

    No Known Activations