© 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. 64996
    Prev
    Next
    INDEX
    Explanations

    names of places and hotels

    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
    是非常
    -1.60
    sioni
    -1.55
    脔
    -1.51
    ggish
    -1.46
    </h3>
    -1.46
    prechung
    -1.42
     fisuras
    -1.39
    metheus
    -1.38
    也只能
    -1.37
    IGATION
    -1.33
    POSITIVE LOGITS
    ↵↵
    2.08
     Usaha
    1.37
     tanpa
    1.37
     você
    1.35
     VIDEOT
    1.31
    gucigalpa
    1.31
    (
    1.31
     Without
    1.27
     Lokasi
    1.27
    ープン
    1.26
    Activations Density 0.018%

    No Known Activations