© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9339
    Prev
    Next
    INDEX
    Explanations

    waiting for time or events

    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
     Даже
    -1.57
     nawet
    -1.47
     trov
    -1.45
    ALLEL
    -1.44
     Многие
    -1.42
     viewed
    -1.41
     regarded
    -1.41
     Именно
    -1.40
    彼は
    -1.38
     gena
    -1.36
    POSITIVE LOGITS
     to
    1.73
    ↵↵
    1.66
     “
    1.41
     like
    1.40
     such
    1.34
     que
    1.30
     that
    1.29
     if
    1.24
    分に
    1.23
    "",
    
    1.20
    Activations Density 0.015%

    No Known Activations