© 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. 34-GEMMASCOPE-RES-131K
    7. 81107
    Prev
    Next
    INDEX
    Explanations

    Lugo, Luhann, luge

    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_34/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
     празд
    -0.77
    たび
    -0.75
     Königs
    -0.74
     Strasse
    -0.73
    という感じ
    -0.73
    existing
    -0.71
    ever
    -0.71
    搡
    -0.70
     Danmark
    -0.70
     наличие
    -0.69
    POSITIVE LOGITS
    Lu
    1.13
     Lu
    0.94
    LU
    0.87
     Lupus
    0.85
    subsec
    0.85
     LUT
    0.85
    .‏
    0.84
    Лу
    0.83
     lou
    0.82
     LUC
    0.82
    Activations Density 0.013%

    No Known Activations