© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12137
    Prev
    Next
    INDEX
    Explanations

    questions and preferences

    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
    歩道
    -0.93
     przecież
    -0.87
    的一些
    -0.85
    你喜欢
    -0.84
    好き
    -0.82
     eventually
    -0.80
     bernama
    -0.78
     some
    -0.78
     вже
    -0.78
    大好きな
    -0.77
    POSITIVE LOGITS
     aucun
    1.00
    .'</
    0.96
    :“……”
    0.93
     spl
    0.91
    currently
    0.90
    <<"\
    0.90
    voller
    0.88
     guilty
    0.87
     gegenwär
    0.85
    iration
    0.85
    Activations Density 0.010%

    No Known Activations