© 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. 10-GEMMASCOPE-RES-131K
    7. 9050
    Prev
    Next
    INDEX
    Explanations

    positive or negative numerical values

    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_10/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
    肏
    -2.02
    lovely
    -1.98
    
    -1.95
    
    -1.89
    罍
    -1.80
    ⚊
    -1.79
     ajudam
    -1.79
    踫
    -1.78
    
    -1.77
    xvi
    -1.76
    POSITIVE LOGITS
    From
    2.92
    With
    2.69
    7
    2.64
    5
    2.63
     for
    2.59
    There
    2.58
    At
    2.52
    2
    2.42
    For
    2.41
    4
    2.34
    Activations Density 0.025%

    No Known Activations