© 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. 118910
    Prev
    Next
    INDEX
    Explanations

    dated, date, dating

    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
     about
    -1.59
    笵
    -1.56
    
    -1.50
     durante
    -1.48
    raan
    -1.48
     resalt
    -1.47
     spécialement
    -1.42
     neues
    -1.41
    犼
    -1.41
    dengan
    -1.40
    POSITIVE LOGITS
    —
    1.57
    of
    1.41
     作り方
    1.34
     sicheren
    1.33
    其他
    1.29
    …！
    1.29
    le
    1.28
    他にも
    1.26
     klubben
    1.26
    O
    1.25
    Activations Density 0.038%

    No Known Activations