© 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. 130633
    Prev
    Next
    INDEX
    Explanations

    programming keywords and identifiers

    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
     своих
    -1.82
     тоже
    -1.71
    appeared
    -1.52
     POSTS
    -1.51
     каждый
    -1.48
     rè
    -1.48
     CALLED
    -1.47
    showed
    -1.45
     $^{\
    -1.45
     был
    -1.45
    POSITIVE LOGITS
     you
    2.64
     of
    2.55
     we
    2.23
    君は
    1.67
     on
    1.56
    dė
    1.53
    writeHead
    1.46
     people
    1.45
    0
    1.43
     this
    1.41
    Activations Density 0.013%

    No Known Activations