© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59532
    Prev
    Next
    INDEX
    Explanations

    second language learning

    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
    鴴
    -1.56
    紧接着
    -1.46
     رع
    -1.45
    個人的には
    -1.42
    诞生
    -1.41
    馓
    -1.41
     capitan
    -1.37
    搖
    -1.36
    ouncement
    -1.34
     padi
    -1.34
    POSITIVE LOGITS
    ингл
    1.48
    ！”
    1.43
    zação
    1.40
    Ἤ
    1.39
     hampir
    1.39
    colata
    1.38
    当然
    1.37
     even
    1.35
     exigencias
    1.34
     fairly
    1.33
    Activations Density 0.011%

    No Known Activations