© 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. 69481
    Prev
    Next
    INDEX
    Explanations

    mona and llama

    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
    十分的
    -2.95
    踅
    -2.66
    
    -2.61
    摃
    -2.58
     are
    -2.56
    谖
    -2.47
     اذا
    -2.47
    IALE
    -2.45
     weren
    -2.39
    潆
    -2.38
    POSITIVE LOGITS
    刧
    2.58
    ?”
    2.53
            
    2.45
    鹚
    2.39
    🎉
    2.39
    }$
    2.30
    <b>
    2.23
     dasarnya
    2.14
    숱
    2.13
    {
    2.11
    Activations Density 0.002%

    No Known Activations