© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99874
    Prev
    Next
    INDEX
    Explanations

    raw types or sockets

    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
    ’
    -4.28
    </h3>
    -2.88
    {
    -2.41
    やった
    -2.34
    也会
    -2.22
     ส่วน
    -2.11
    $
    -2.05
     แต่
    -2.05
    ↵
    -2.03
     The
    -2.00
    POSITIVE LOGITS
     multitude
    3.00
     esteemed
    2.67
    呖
    2.56
    鷓
    2.55
     coveted
    2.50
     myriad
    2.47
    嘬
    2.44
    ௜
    2.44
     программы
    2.38
    
    2.34
    Activations Density 0.006%

    No Known Activations