© 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. 42030
    Prev
    Next
    INDEX
    Explanations

    parentheses and mathematical expressions

    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
    ↵
    -2.33
    le
    -2.00
    la
    -1.99
    ang
    -1.98
    ge
    -1.97
    嗞
    -1.91
     informée
    -1.89
    »،
    -1.88
    ga
    -1.85
    uk
    -1.85
    POSITIVE LOGITS
        
    2.13
     MOST
    1.97
    </strong>
    1.96
    ны
    1.86
    玊
    1.85
     για
    1.83
             
    1.80
    rased
    1.78
    AddHtmlAttribute
    1.77
    pushFollow
    1.76
    Activations Density 0.018%

    No Known Activations