© 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. 10-GEMMASCOPE-RES-131K
    7. 73567
    Prev
    Next
    INDEX
    Explanations

    country codes and names

    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
     about
    -2.47
     one
    -1.69
     until
    -1.66
     Menggunakan
    -1.59
     or
    -1.58
     gratific
    -1.53
    หรือ
    -1.53
     your
    -1.52
    cznych
    -1.52
     palestra
    -1.49
    POSITIVE LOGITS
     they
    1.64
    都沒
    1.60
    脚步
    1.59
    ֶּ
    1.58
     
    1.55
    嚕
    1.54
     incroy
    1.48
     pertanto
    1.48
     schreiben
    1.46
     Маль
    1.44
    Activations Density 0.031%

    No Known Activations