© 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. 57476
    Prev
    Next
    INDEX
    Explanations

    thumbnail images and previews

    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
    -1.96
    "?
    -1.89
    said
    -1.67
     torner
    -1.66
     Dlatego
    -1.61
     {
    -1.59
     rapida
    -1.58
    -1.58
    "}>
    -1.58
    "]
    -1.55
    POSITIVE LOGITS
    </h2>
    1.99
     conectados
    1.89
    臜
    1.82
    '
    1.79
    紧接着
    1.69
    此时的
    1.68
    诸多
    1.66
     cerrados
    1.65
    硬盘
    1.62
    别人的
    1.60
    Activations Density 0.010%

    No Known Activations