© 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. 61104
    Prev
    Next
    INDEX
    Explanations

    month of [month name]

    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
    即可
    -1.43
     present
    -1.34
     Там
    -1.32
    {
    -1.31
     united
    -1.31
    >
    -1.30
     bezeichnet
    -1.29
     devise
    -1.28
     formie
    -1.27
     sehe
    -1.26
    POSITIVE LOGITS
    櫚
    1.80
    Weitere
    1.72
     persönliche
    1.70
    鼯
    1.70
    人也
    1.69
    了一句
    1.68
    .''
    1.66
    ються
    1.64
     exempel
    1.61
    Setiap
    1.59
    Activations Density 0.009%

    No Known Activations