© 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. 11335
    Prev
    Next
    INDEX
    Explanations

    heavy, dull, or tired states

    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
    Татьяна
    -1.39
     correspon
    -1.35
     عندما
    -1.34
    そこから
    -1.33
     ultime
    -1.31
    那就
    -1.31
    Australie
    -1.31
    什么样的
    -1.31
    캇
    -1.30
     facilite
    -1.29
    POSITIVE LOGITS
     With
    1.84
     WITH
    1.78
     not
    1.69
     dengan
    1.68
     με
    1.58
     avec
    1.55
     עם
    1.49
    {
    1.49
     với
    1.46
    mathrm
    1.38
    Activations Density 0.053%

    No Known Activations