© 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. 821
    Prev
    Next
    INDEX
    Explanations

    view or json response

    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
    phère
    -1.56
    )…
    -1.55
    …)
    -1.44
     nimmer
    -1.39
     Others
    -1.38
    Xoxo
    -1.38
    ;',
    -1.34
     знать
    -1.34
    рую
    -1.32
    ؛
    -1.32
    POSITIVE LOGITS
    昔から
    1.55
    你是不是
    1.54
     anspruchs
    1.52
     folgenden
    1.50
    プレミアム
    1.49
    にほん
    1.45
     slams
    1.41
    你也
    1.41
     your
    1.39
     collè
    1.38
    Activations Density 0.001%

    No Known Activations