© 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. 11124
    Prev
    Next
    INDEX
    Explanations

    time and duration or requirement

    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
     our
    -1.52
    ୌ
    -1.43
     your
    -1.41
     preocupado
    -1.39
    珰
    -1.36
     asust
    -1.34
    -1.33
     reise
    -1.32
     nime
    -1.31
    🦣
    -1.31
    POSITIVE LOGITS
    :
    1.30
    ang
    1.26
     fuera
    1.24
     olden
    1.21
     vermutlich
    1.21
    l
    1.20
     gastron
    1.16
    辄
    1.16
     sicherlich
    1.16
    m
    1.16
    Activations Density 0.014%

    No Known Activations