© 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. 10020
    Prev
    Next
    INDEX
    Explanations

    slat design

    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
     セレ
    -2.55
    
    -2.30
     schien
    -2.30
    .
    -2.28
     obno
    -2.22
    锉
    -2.19
    蛲
    -2.17
     zaczą
    -2.14
     Our
    -2.13
    %;
    -2.13
    POSITIVE LOGITS
    寕
    2.61
     erbjuder
    2.59
    但是在
    2.50
    ()]);
    2.44
    spesies
    2.41
    鄚
    2.39
    是我们
    2.30
    了什么
    2.28
     behövs
    2.22
    ст
    2.19
    Activations Density 0.078%

    No Known Activations