© 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. 48176
    Prev
    Next
    INDEX
    Explanations

    New York Times weekend sections

    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
     Guay
    -0.81
    🧆
    -0.81
     jambes
    -0.77
    няли
    -0.74
    トラブル
    -0.73
     hurrying
    -0.72
    അ
    -0.72
    losigkeit
    -0.72
    MPP
    -0.72
    kungen
    -0.71
    POSITIVE LOGITS
     lifestyle
    1.28
     Arts
    1.27
     weekend
    1.27
     Sunday
    1.24
     Weekend
    1.22
     section
    1.21
     supplement
    1.19
     Section
    1.16
     Lifestyle
    1.15
     arts
    1.14
    Activations Density 0.036%

    No Known Activations