© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60121
    Prev
    Next
    INDEX
    Explanations

    save life or lives

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

    phrases about saving lives or loss of life, particularly in contexts of death, suicide, or rescue efforts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vicky
    -0.73
     Katrina
    -0.72
    atto
    -0.71
     السيارة
    -0.71
    queado
    -0.71
    κα
    -0.69
     bekommt
    -0.69
    ід
    -0.69
    FTS
    -0.68
    жье
    -0.68
    POSITIVE LOGITS
     lives
    4.88
     life
    3.58
    lives
    3.39
     Lives
    3.19
    Lives
    3.08
     LIVES
    2.86
     жизнь
    2.84
     vidas
    2.75
     життя
    2.72
     жизни
    2.70
    Activations Density 0.030%

    No Known Activations