© 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. 22-GEMMASCOPE-RES-131K
    7. 71570
    Prev
    Next
    INDEX
    Explanations

    learning and finding solutions

    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_22/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
    ticles
    -0.79
    📆
    -0.79
    waitUntil
    -0.79
    ibição
    -0.75
    曉
    -0.73
    crania
    -0.71
     شيئ
    -0.71
     akci
    -0.70
    naf
    -0.69
    anganan
    -0.69
    POSITIVE LOGITS
     learning
    1.45
     lessons
    1.40
     learn
    1.34
     future
    1.30
     lesson
    1.25
    lessons
    1.23
     teach
    1.20
     Learning
    1.16
     test
    1.16
    learning
    1.16
    Activations Density 0.096%

    No Known Activations