© 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. 84633
    Prev
    Next
    INDEX
    Explanations

    dating buildings and sites

    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
     muere
    -0.83
    gerea
    -0.83
    Altre
    -0.81
    umacher
    -0.80
    hiers
    -0.79
    altro
    -0.78
     across
    -0.76
     כדי
    -0.75
     luxurious
    -0.75
     закончи
    -0.74
    POSITIVE LOGITS
     dating
    5.31
    dating
    4.16
     Dating
    3.92
     dates
    3.86
    Dating
    3.75
     dated
    3.72
     date
    3.42
    dates
    2.89
     Dates
    2.78
    dated
    2.63
    Activations Density 0.104%

    No Known Activations