© 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. 35870
    Prev
    Next
    INDEX
    Explanations

    package names, code keywords, and names

    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
     participé
    -1.03
    arım
    -0.94
    鞣
    -0.93
     when
    -0.91
     only
    -0.91
    $.}
    -0.88
     where
    -0.87
     all
    -0.86
    resave
    -0.86
    yakit
    -0.85
    POSITIVE LOGITS
     osserv
    1.01
     shroud
    0.94
    有一個
    0.93
     revamped
    0.92
    tian
    0.92
     Lately
    0.91
     latter
    0.91
    なるべく
    0.91
     impone
    0.90
     装修
    0.88
    Activations Density 0.000%

    No Known Activations