© 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. 13819
    Prev
    Next
    INDEX
    Explanations

    Tpl or layout file paths

    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
     também
    -1.08
     示例
    -1.05
     化
    -1.05
     akku
    -1.00
     щодо
    -0.99
    甚至
    -0.96
     encontré
    -0.96
    𝓵
    -0.94
    픈
    -0.93
     Thanks
    -0.92
    POSITIVE LOGITS
    暌
    1.09
    Mice
    1.08
    льника
    1.06
    一辆
    1.02
     huile
    1.02
     noix
    0.98
    Sectors
    0.98
     Mice
    0.96
     montagne
    0.95
     dicho
    0.94
    Activations Density 0.000%

    No Known Activations