© 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. 9932
    Prev
    Next
    INDEX
    Explanations

    for purpose or outcome

    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
     antiguos
    -2.13
     tradicionales
    -2.05
     unending
    -1.97
    の葉
    -1.95
    puerta
    -1.89
    ᐠ
    -1.88
     raiſ
    -1.86
    ᥬ
    -1.86
    Recept
    -1.82
     recientes
    -1.80
    POSITIVE LOGITS
     and
    3.31
     to
    2.33
    re
    2.25
     which
    2.13
     During
    1.95
    t
    1.84
     While
    1.77
    [
    1.74
    J
    1.71
     whom
    1.70
    Activations Density 0.026%

    No Known Activations