© 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. 86980
    Prev
    Next
    INDEX
    Explanations

    number and punctuation sequences

    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
     to
    -1.95
    
    -1.59
    ।
    -1.47
    quelize
    -1.46
     ")
    -1.45
     which
    -1.44
    我们是
    -1.40
     enthousi
    -1.37
    却被
    -1.37
     who
    -1.37
    POSITIVE LOGITS
     Bardzo
    1.59
    environments
    1.45
    อื่น
    1.43
    บน
    1.43
    その他
    1.41
    .
    1.41
     ждать
    1.41
    aneously
    1.39
     then
    1.37
     Voraussetzung
    1.36
    Activations Density 0.005%

    No Known Activations