© 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. 92253
    Prev
    Next
    INDEX
    Explanations

    millions, thousands, dozens

    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
     Almost
    -0.91
    秤
    -0.82
     casi
    -0.82
    şağı
    -0.79
     very
    -0.76
     мере
    -0.74
    大半
    -0.74
    絃
    -0.74
     only
    -0.73
     shortly
    -0.73
    POSITIVE LOGITS
     hundred
    3.22
     thousand
    3.08
     ten
    2.80
     dozen
    2.64
     million
    2.55
    hundred
    2.53
     fifty
    2.42
    thousand
    2.34
     twenty
    2.27
     десять
    2.14
    Activations Density 0.082%

    No Known Activations