© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129204
    Prev
    Next
    INDEX
    Explanations

    X-UA-Compatible meta tag

    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
     bazı
    -1.95
     alcuni
    -1.69
     algún
    -1.59
    0
    -1.56
     [
    -1.49
     Infór
    -1.45
     associés
    -1.44
     alcune
    -1.42
     algunas
    -1.41
     kanske
    -1.41
    POSITIVE LOGITS
     moverse
    1.46
     تھے
    1.46
    几十
    1.45
    
    1.43
    工事
    1.42
     гостей
    1.42
    活动的
    1.40
    ־ה
    1.38
     remarkable
    1.38
    ſtra
    1.37
    Activations Density 0.000%

    No Known Activations