© 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. 104947
    Prev
    Next
    INDEX
    Explanations

    dimensions: tall, wide, thin, thick, heavy

    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
     of
    -1.58
    䰀
    -1.57
     his
    -1.56
    鈈
    -1.48
    .
    -1.46
    もしっかり
    -1.42
    in
    -1.42
     sítio
    -1.41
    いいのか
    -1.41
    dryer
    -1.37
    POSITIVE LOGITS
     обязательно
    1.73
    ValueGeneration
    1.70
     всегда
    1.63
    áře
    1.55
     pauvre
    1.54
     Wiking
    1.51
     какая
    1.50
     мы
    1.49
     быстро
    1.45
     какой
    1.45
    Activations Density 0.042%

    No Known Activations