© 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. 69878
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     我们
    -1.86
    佧
    -1.85
    in
    -1.83
     What
    -1.82
     tries
    -1.77
    ina
    -1.76
     Usually
    -1.74
     {
    -1.73
    ā
    -1.72
     There
    -1.69
    POSITIVE LOGITS
     automóviles
    1.95
    犼
    1.91
    alakip
    1.83
     elektrische
    1.81
    へ向
    1.75
     gustaMe
    1.73
    に戻る
    1.71
     pouvons
    1.71
     aleación
    1.71
     canaux
    1.70
    Activations Density 0.010%

    No Known Activations