© 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. 65003
    Prev
    Next
    INDEX
    Explanations

    verb followed by particle

    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
    Fußball
    -1.45
     while
    -1.44
     elefante
    -1.38
     without
    -1.35
     presumably
    -1.30
     with
    -1.27
     one
    -1.26
    তথ্য
    -1.26
     ensure
    -1.23
    Abend
    -1.23
    POSITIVE LOGITS
     Բ
    1.39
    ratto
    1.27
     nier
    1.21
    っと
    1.18
    อ่าน
    1.17
    服务的
    1.16
     prace
    1.16
     mamy
    1.16
     être
    1.16
     anomalies
    1.13
    Activations Density 0.137%

    No Known Activations