© 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. 25581
    Prev
    Next
    INDEX
    Explanations

    power generation

    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
     aceptas
    -0.78
     prestar
    -0.77
    男友
    -0.73
    匿
    -0.72
     properly
    -0.69
     gás
    -0.66
     сто
    -0.65
    namiento
    -0.65
    亟
    -0.64
     collected
    -0.64
    POSITIVE LOGITS
     generation
    0.96
    generation
    0.91
     Generation
    0.91
     generación
    0.86
    modium
    0.85
    浓郁
    0.83
    tschaft
    0.80
    ソッド
    0.79
     GENERATION
    0.79
    XDECREF
    0.79
    Activations Density 0.006%

    No Known Activations