© 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. 22-GEMMASCOPE-RES-131K
    7. 36339
    Prev
    Next
    INDEX
    Explanations

    days or dates

    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_22/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
    每天
    -1.46
    daily
    -1.13
     daily
    -1.11
    DAILY
    -1.04
    期間
    -1.01
    Daily
    -0.96
    していきます
    -0.92
    每日
    -0.90
     возможностей
    -0.90
    日常
    -0.89
    POSITIVE LOGITS
    那天
    1.04
     day
    1.02
     günü
    0.94
    當天
    0.91
    day
    0.85
    День
    0.83
     Saturday
    0.79
     concert
    0.79
    ItemList
    0.78
    entretien
    0.77
    Activations Density 0.122%

    No Known Activations