© 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. 35990
    Prev
    Next
    INDEX
    Explanations

    digital ownership and virtual assets

    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
     ikke
    -1.23
     אבל
    -1.21
    🏟
    -1.20
     need
    -1.16
     azulejos
    -1.12
    velocityX
    -1.11
    贏
    -1.11
     adequate
    -1.11
     used
    -1.09
     ett
    -1.09
    POSITIVE LOGITS
    了一口气
    1.52
     femenina
    1.49
     vinculados
    1.41
     protegido
    1.41
    atán
    1.39
    的看着
    1.38
    amerikanischer
    1.34
     слой
    1.33
     упаковка
    1.33
    笑了笑
    1.31
    Activations Density 0.003%

    No Known Activations