© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34857
    Prev
    Next
    INDEX
    Explanations

    React component props

    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
    mybatisplus
    -0.93
    namental
    -0.93
    oftware
    -0.92
    ¢
    -0.92
     violencia
    -0.91
    itarian
    -0.90
    sters
    -0.89
    тивні
    -0.88
    strftime
    -0.88
     scal
    -0.87
    POSITIVE LOGITS
     before
    1.00
     then
    0.92
     führten
    0.90
     felic
    0.90
     adequ
    0.89
    ренко
    0.87
     or
    0.85
    muñeca
    0.85
     available
    0.83
    状况
    0.83
    Activations Density 0.002%

    No Known Activations