© 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. 22-GEMMASCOPE-RES-131K
    4. 75363
    Prev
    Next
    INDEX
    Explanations

    positive emotions and events

    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_22/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
    DataGridView
    -0.90
    Recv
    -0.88
    
    -0.86
    ch
    -0.83
     najwięks
    -0.82
     太郎
    -0.81
     modific
    -0.80
    !';
    -0.79
    сила
    -0.78
     така
    -0.77
    POSITIVE LOGITS
     positive
    1.13
    Positive
    0.98
    ">+
    0.98
     aislada
    0.98
     entgeg
    0.97
     dificuldade
    0.96
    찾
    0.94
    뒤
    0.94
     uplifting
    0.93
    POSITIVE
    0.92
    Activations Density 0.150%

    No Known Activations