© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60029
    Prev
    Next
    INDEX
    Explanations

    truly followed by positive adjectives

    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
    ers
    -2.00
    了很多
    -1.77
    use
    -1.66
    out
    -1.66
    return
    -1.64
     ۱۴
    -1.62
    uring
    -1.61
    しゃぶ
    -1.59
    是想
    -1.55
     The
    -1.55
    POSITIVE LOGITS
     могут
    1.97
     provincias
    1.55
    namese
    1.50
     localidades
    1.49
    caneca
    1.48
     .”
    1.46
    ，”
    1.45
     truly
    1.45
     можуть
    1.44
     macetas
    1.43
    Activations Density 0.013%

    No Known Activations