© 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. 80583
    Prev
    Next
    INDEX
    Explanations

    activities and places outdoors

    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
    蟜
    -2.92
    躄
    -2.59
    醅
    -2.56
     は
    -2.28
     と
    -2.25
     bekende
    -2.22
    桄
    -2.19
    
    -2.17
     aiding
    -2.16
    かっこいい
    -2.14
    POSITIVE LOGITS
    ,.
    2.94
    s
    2.80
    .
    2.69
     are
    2.61
    料
    2.58
    pecabe
    2.52
     we
    2.47
    er
    2.45
    但我
    2.41
    {
    2.31
    Activations Density 0.005%

    No Known Activations