© 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. 22-GEMMASCOPE-RES-131K
    7. 54134
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations

    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_22/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
    lösen
    -0.76
     intangible
    -0.75
    NSON
    -0.75
     mexican
    -0.72
    logfile
    -0.71
    后者
    -0.71
     pace
    -0.70
    蜘
    -0.70
    pozdrawiam
    -0.69
    Rhode
    -0.69
    POSITIVE LOGITS
    第一
    0.85
    言
    0.84
    第一个
    0.82
    Words
    0.80
     הראשון
    0.80
    жного
    0.79
     cominci
    0.76
     erste
    0.76
     villages
    0.75
    Singleton
    0.74
    Activations Density 0.041%

    No Known Activations