© 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. 33787
    Prev
    Next
    INDEX
    Explanations

    cruel or harsh situations

    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
    script
    -0.79
    日子
    -0.79
     consternation
    -0.77
    語る
    -0.77
    お部屋
    -0.77
    Люди
    -0.76
    髣
    -0.76
     disgraced
    -0.76
    ляются
    -0.75
    IMPORTED
    -0.75
    POSITIVE LOGITS
     cruel
    3.45
     harsh
    2.86
    cruel
    2.70
     unfor
    2.36
    Cruel
    2.31
     Cruel
    2.20
     cruelty
    2.11
     brutal
    2.05
     unkind
    1.98
     merciless
    1.94
    Activations Density 0.058%

    No Known Activations