© 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. 70589
    Prev
    Next
    INDEX
    Explanations

    waiting

    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
    どのように
    -1.42
    驀
    -1.32
    ࠬ
    -1.31
    ?”
    -1.26
    튿
    -1.23
     .”
    -1.22
     récemment
    -1.18
    ”?
    -1.18
     cansado
    -1.16
     الجميع
    -1.14
    POSITIVE LOGITS
     Deze
    1.46
     medži
    1.41
     Waiting
    1.38
    ⢌
    1.36
    medim
    1.32
     antics
    1.31
     midst
    1.30
     impactful
    1.28
    会い
    1.25
    сятся
    1.23
    Activations Density 0.011%

    No Known Activations