© 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. 23630
    Prev
    Next
    INDEX
    Explanations

    fashion trends and popular styles

    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
    ехали
    -0.86
     edildi
    -0.82
    用の
    -0.82
    rillo
    -0.81
    title
    -0.81
     '/':
    -0.80
    ἄ
    -0.79
    performance
    -0.79
    Beno
    -0.79
    ĝo
    -0.77
    POSITIVE LOGITS
     trend
    3.89
     trends
    3.88
     trending
    2.94
     Trends
    2.89
     trendy
    2.86
    trend
    2.69
     Trend
    2.67
    trends
    2.67
    Trend
    2.56
    Trends
    2.53
    Activations Density 0.082%

    No Known Activations