© 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. 66410
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     into
    -0.94
     to
    -0.93
     magasiner
    -0.81
     sene
    -0.80
     mika
    -0.80
     kela
    -0.77
     linden
    -0.75
     Latham
    -0.75
     Сегодня
    -0.74
     pepe
    -0.73
    POSITIVE LOGITS
    四方
    0.78
    寒
    0.77
     kendisi
    0.76
     jsme
    0.76
     רק
    0.75
    鱉
    0.75
     Recipes
    0.75
    ちは
    0.73
     endeavor
    0.72
    splits
    0.71
    Activations Density 0.021%

    No Known Activations