© 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. 83410
    Prev
    Next
    INDEX
    Explanations

    names like elisa, eliza, and lisa

    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
    dington
    -0.76
    supposed
    -0.74
     السياسة
    -0.73
     четыре
    -0.71
     vienas
    -0.70
     sentirse
    -0.69
    lili
    -0.69
     spraw
    -0.69
    璽
    -0.69
    proteins
    -0.68
    POSITIVE LOGITS
    beth
    1.29
    beta
    1.04
    Beth
    0.94
    ktı
    0.80
     solicita
    0.77
     втор
    0.76
    chnen
    0.75
     Picard
    0.75
    вета
    0.74
    库存
    0.74
    Activations Density 0.027%

    No Known Activations