© 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. 39248
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
    -1.05
    และ
    -0.99
     также
    -0.98
    kapital
    -0.96
     induk
    -0.94
     również
    -0.93
    simply
    -0.93
     även
    -0.91
    皮肤
    -0.91
     également
    -0.90
    POSITIVE LOGITS
     it
    0.96
     still
    0.94
     existing
    0.87
    褔
    0.87
    的问道
    0.85
     touted
    0.85
     riten
    0.85
     could
    0.84
    まります
    0.83
     einiger
    0.82
    Activations Density 0.003%

    No Known Activations