© 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. 34-GEMMASCOPE-RES-131K
    7. 23854
    Prev
    Next
    INDEX
    Explanations

    early education and placeholders

    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_34/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
    owski
    -0.83
     School
    -0.78
     口
    -0.75
     Student
    -0.75
     eden
    -0.74
    QL
    -0.73
    ophilus
    -0.73
     Rare
    -0.72
    ICA
    -0.71
     trebu
    -0.71
    POSITIVE LOGITS
    juegos
    1.00
     games
    0.97
     game
    0.90
     activities
    0.88
    Synopsis
    0.86
     children
    0.85
     play
    0.85
     circle
    0.83
    juego
    0.83
    segundo
    0.81
    Activations Density 0.001%

    No Known Activations