© 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. 75208
    Prev
    Next
    INDEX
    Explanations

    actions and violations

    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
     правительства
    -1.55
     біль
    -1.47
     semula
    -1.41
     selepas
    -1.40
     more
    -1.39
     الماء
    -1.38
     three
    -1.37
     begin
    -1.35
     chileno
    -1.34
     сахара
    -1.34
    POSITIVE LOGITS
    🧫
    1.63
    镲
    1.61
    ⁝
    1.59
    𝐳
    1.56
     бампер
    1.55
    摀
    1.54
    
    1.52
    genheit
    1.48
    𓏸
    1.48
     estadía
    1.46
    Activations Density 0.100%

    No Known Activations