© 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. 71258
    Prev
    Next
    INDEX
    Explanations

    preventing disclosure

    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
     Crooked
    -1.00
    BOOKS
    -0.94
     انتظار
    -0.94
     rapporter
    -0.91
    问
    -0.90
    ⏬
    -0.89
     sauve
    -0.89
    lösung
    -0.89
     occuper
    -0.89
     attente
    -0.88
    POSITIVE LOGITS
     information
    1.48
     public
    1.25
     valuable
    1.24
     data
    1.22
     disclosure
    1.20
     disclosed
    1.16
     identifying
    1.14
     publicly
    1.13
     exposed
    1.09
     revealing
    1.06
    Activations Density 0.072%

    No Known Activations