© 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. 10-GEMMASCOPE-RES-131K
    7. 12075
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation followed by words

    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_10/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
    {
    -1.95
    forKey
    -1.65
    欸
    -1.57
     organes
    -1.52
    umt
    -1.51
    leſs
    -1.51
    ishes
    -1.48
     关闭
    -1.46
    ine
    -1.44
    IONE
    -1.43
    POSITIVE LOGITS
    縢
    1.73
     help
    1.73
    葙
    1.72
     dispoz
    1.62
    because
    1.53
     multitude
    1.53
     esteemed
    1.52
    临床
    1.48
    鞋子
    1.48
     influential
    1.48
    Activations Density 0.001%

    No Known Activations