© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49913
    Prev
    Next
    INDEX
    Explanations

    expressing sympathy for loss

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    砖
    -0.83
    destin
    -0.79
     dacht
    -0.78
     Atem
    -0.77
     respiración
    -0.77
    ラミ
    -0.76
     celebration
    -0.75
    磚
    -0.75
    养老
    -0.75
     punishing
    -0.75
    POSITIVE LOGITS
     condolences
    3.20
     condolence
    2.11
     sympathy
    1.96
     sympathies
    1.79
    Condolences
    1.69
     Condol
    1.64
     condo
    1.39
     condol
    1.33
    symp
    1.32
    Symp
    1.30
    Activations Density 0.006%

    No Known Activations