© 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. 48359
    Prev
    Next
    INDEX
    Explanations

    `.htm"

    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
     impecable
    -1.73
     初始化
    -1.72
     then
    -1.70
    GOING
    -1.70
    níky
    -1.68
     سپس
    -1.63
     balle
    -1.61
     creme
    -1.59
     Boletín
    -1.58
    Daha
    -1.57
    POSITIVE LOGITS
     all
    2.20
     no
    2.19
     with
    2.19
     other
    2.06
     not
    2.00
    </b>
    1.90
    </em>
    1.80
     different
    1.77
     four
    1.72
     only
    1.70
    Activations Density 0.027%

    No Known Activations