© 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. 84629
    Prev
    Next
    INDEX
    Explanations

    programming tools and libraries

    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
     всех
    -1.23
     alles
    -1.05
     ингреди
    -0.96
    🕗
    -0.94
    および
    -0.94
    GridColumn
    -0.93
    everything
    -0.92
     wszystkie
    -0.92
    では
    -0.92
     همه
    -0.92
    POSITIVE LOGITS
     this
    1.27
     different
    1.27
     another
    1.09
     while
    1.07
     provided
    1.03
     your
    1.02
    +=
    1.02
     their
    1.02
     some
    1.00
     with
    0.98
    Activations Density 0.267%

    No Known Activations