© 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. 69769
    Prev
    Next
    INDEX
    Explanations

    please visit, try doing

    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
     "
    -1.86
     '
    -1.77
     его
    -1.73
     和
    -1.69
     '.
    -1.66
     Вене
    -1.63
     was
    -1.59
    .'"
    -1.58
    皤
    -1.55
     gets
    -1.49
    POSITIVE LOGITS
    ,”
    1.92
    摃
    1.91
    我們
    1.87
     disregarding
    1.84
     スクリーン
    1.80
     adatta
    1.80
     Versuche
    1.79
    owią
    1.79
    ….”
    1.78
    livro
    1.75
    Activations Density 0.001%

    No Known Activations