© 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. 104952
    Prev
    Next
    INDEX
    Explanations

    infinitive verb phrases describing methods

    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
    (!__
    -1.61
    schermata
    -1.53
     thoſe
    -1.51
    coupe
    -1.49
    motorola
    -1.48
    astres
    -1.48
    unitOfWork
    -1.45
    +/**
    -1.41
    dutch
    -1.41
     ursprünglich
    -1.39
    POSITIVE LOGITS
     at
    1.88
    '
    1.83
    respect
    1.61
     julio
    1.56
     febrero
    1.50
    ჱ
    1.46
     umiejęt
    1.45
    薷
    1.43
    やん
    1.43
     avoir
    1.42
    Activations Density 0.076%

    No Known Activations