© 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. 9197
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
    ῞
    -3.39
    ⑊
    -3.27
    說
    -3.16
    ㍑
    -3.13
    神
    -3.03
    
    -3.03
    澁
    -2.98
    鬭
    -2.95
    袿
    -2.91
    ޏ
    -2.89
    POSITIVE LOGITS
    “
    4.34
    d
    3.34
    [
    3.20
     When
    2.88
    ]
    2.72
    ...
    2.66
     “
    2.64
     be
    2.61
    {
    2.61
     As
    2.55
    Activations Density 0.044%

    No Known Activations