© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25498
    Prev
    Next
    INDEX
    Explanations

    months and numbers in various languages

    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
     sogni
    -1.04
     Chinois
    -1.00
    
    -0.99
     personaggi
    -0.99
     tarte
    -0.97
     Chambres
    -0.96
     בנושא
    -0.94
     schreef
    -0.91
     kolam
    -0.91
    ↑↑↑
    -0.90
    POSITIVE LOGITS
     május
    1.11
     пять
    1.01
     április
    1.00
     два
    0.96
     július
    0.95
    了一口气
    0.93
     почти
    0.93
     Organic
    0.93
     március
    0.91
     június
    0.90
    Activations Density 0.060%

    No Known Activations