© 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. 109604
    Prev
    Next
    INDEX
    Explanations

    emotions and tensions rise

    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
     Quizzes
    -0.87
    rennen
    -0.81
    quests
    -0.81
     устрой
    -0.81
    requency
    -0.80
    érez
    -0.79
     дому
    -0.77
     sayfası
    -0.77
     Kurdistan
    -0.76
    整形
    -0.76
    POSITIVE LOGITS
     tensions
    3.91
     emotions
    3.66
     temp
    3.20
     tension
    3.19
     passions
    2.83
     Emotions
    2.72
    Emotions
    2.69
    emotions
    2.48
    Temp
    2.33
     Temp
    2.30
    Activations Density 0.076%

    No Known Activations