© 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. 76168
    Prev
    Next
    INDEX
    Explanations

    fashion and lifestyle magazines

    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
    "?>
    -0.94
    Erstellt
    -0.88
    ்த்த
    -0.81
    Дмитрий
    -0.80
     cappella
    -0.79
     odpad
    -0.78
    chandise
    -0.77
    탭
    -0.77
    felde
    -0.76
     Bracelet
    -0.76
    POSITIVE LOGITS
     magazine
    1.95
     Vogue
    1.85
     Magazine
    1.55
     magazines
    1.55
     Harper
    1.49
    Vogue
    1.43
     Elle
    1.41
     GQ
    1.35
     fashion
    1.25
     glossy
    1.20
    Activations Density 0.043%

    No Known Activations