© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129858
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

    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
     to
    -2.02
     puis
    -1.82
     it
    -1.72
     tujuan
    -1.68
     kemudian
    -1.62
    稔
    -1.58
    providedIn
    -1.54
    yakit
    -1.51
    vgili
    -1.50
    氿
    -1.48
    POSITIVE LOGITS
    There
    2.06
    还是很
    1.98
    9
    1.93
    4
    1.92
    時的
    1.91
    肯定会
    1.90
    Recently
    1.89
    5
    1.85
    Depending
    1.84
    不过是
    1.84
    Activations Density 0.004%

    No Known Activations