© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69137
    Prev
    Next
    INDEX
    Explanations

    indexed items

    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
    梳
    -0.81
    flan
    -0.79
     مستقیم
    -0.74
     CROSS
    -0.74
    􏰀
    -0.73
    james
    -0.73
     SILVER
    -0.73
     voir
    -0.73
     write
    -0.72
    有什么
    -0.72
    POSITIVE LOGITS
     another
    1.98
    Another
    1.55
    อีก
    1.29
     Another
    1.21
    another
    1.16
    另一個
    1.16
     další
    1.14
     second
    1.14
    別の
    1.04
    Еще
    0.96
    Activations Density 0.071%

    No Known Activations