© 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. 11991
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or notation

    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
    好吃的
    -1.48
     encontram
    -1.48
    ÇÕES
    -1.48
    难受
    -1.43
    是什麼
    -1.43
     procurando
    -1.39
    以外の
    -1.38
    詎
    -1.37
     hasn
    -1.36
    1
    -1.36
    POSITIVE LOGITS
    您的
    1.72
    اما
    1.63
     ataupun
    1.60
    ”
    1.57
     your
    1.55
    ６
    1.53
    Ｅ
    1.52
    vlá
    1.52
     бъдат
    1.49
    Ｔ
    1.49
    Activations Density 0.045%

    No Known Activations