© 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. 90544
    Prev
    Next
    INDEX
    Explanations

    anger management

    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
     утра
    -0.76
     bảo
    -0.73
    日起
    -0.71
     behaves
    -0.69
     рассе
    -0.67
     Zusammenfassung
    -0.66
     ح
    -0.65
     headed
    -0.65
     projects
    -0.64
     false
    -0.63
    POSITIVE LOGITS
     Anger
    1.10
    Anger
    1.08
    management
    1.02
     management
    1.01
    Management
    0.96
     MANAGEMENT
    0.94
     anger
    0.90
    MANAGEMENT
    0.89
    Issues
    0.88
     ISSUES
    0.85
    Activations Density 0.045%

    No Known Activations