© 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. 10-GEMMASCOPE-RES-131K
    7. 61062
    Prev
    Next
    INDEX
    Explanations

    journaling, reading, sponsored content, promises

    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_10/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
    ּוֹ
    -1.73
    pography
    -1.63
    ִּ
    -1.56
    的一個
    -1.56
     السياس
    -1.48
     violeta
    -1.43
    ֶּ
    -1.43
    ύ
    -1.36
    ַּ
    -1.36
    来讲
    -1.34
    POSITIVE LOGITS
    𝑈
    2.06
     who
    1.81
    んでる
    1.70
     chapéu
    1.70
     relógio
    1.67
    んだり
    1.67
     protože
    1.66
    𝑄
    1.60
    因為
    1.59
     alguien
    1.56
    Activations Density 0.129%

    No Known Activations