© 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. 41251
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical symbols

    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
     autres
    -1.75
     also
    -1.62
     ook
    -1.58
     andere
    -1.52
     aussi
    -1.52
    衣裙
    -1.51
     granja
    -1.50
     otros
    -1.49
     ______
    -1.49
     altri
    -1.47
    POSITIVE LOGITS
     about
    1.67
     which
    1.60
     to
    1.57
     by
    1.42
     from
    1.41
     omtrent
    1.34
    疍
    1.33
    inerario
    1.30
    weiterlesen
    1.30
    visita
    1.30
    Activations Density 0.029%

    No Known Activations