© 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. 22-GEMMASCOPE-RES-131K
    7. 28383
    Prev
    Next
    INDEX
    Explanations

    punctuation and code constructs

    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_22/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
    chede
    -0.96
    ícias
    -0.95
    indade
    -0.92
     empie
    -0.89
    jän
    -0.89
     industriales
    -0.88
    ñoz
    -0.86
     constitue
    -0.85
    尝试
    -0.84
     estiver
    -0.84
    POSITIVE LOGITS
    のだろう
    0.92
    guerite
    0.91
    gadas
    0.90
     if
    0.89
    のだろうか
    0.87
     sappiamo
    0.87
     tbody
    0.85
    ameran
    0.84
     erforderlich
    0.83
     hetzelfde
    0.82
    Activations Density 0.027%

    No Known Activations