© 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. 14575
    Prev
    Next
    INDEX
    Explanations

    XML/code block start markers

    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
    на
    -2.16
     в
    -2.11
     in
    -2.09
    вым
    -2.03
    ?"
    -1.98
     在
    -1.98
    j
    -1.95
    SqlClient
    -1.94
    судар
    -1.94
     در
    -1.93
    POSITIVE LOGITS
    紧接着
    2.28
    嘍
    2.17
    controlador
    2.13
     exemplaires
    2.09
     あと
    1.94
    獁
    1.94
     ($('#
    1.91
     spelers
    1.91
    と思ったら
    1.90
     國際
    1.88
    Activations Density 0.006%

    No Known Activations