© 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. 90648
    Prev
    Next
    INDEX
    Explanations

    foreign characters and names

    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
    to
    -3.00
    n
    -2.80
    ⢊
    -2.78
    er
    -2.73
    which
    -2.66
     détaillés
    -2.56
     pouvez
    -2.52
    忪
    -2.50
    al
    -2.41
    кроссовки
    -2.39
    POSITIVE LOGITS
     "
    2.92
     \
    2.84
    ଃ
    2.81
     \\
    2.70
     justo
    2.61
    𝄆
    2.61
    "
    2.58
    了一
    2.58
    '
    2.56
    偸
    2.52
    Activations Density 0.003%

    No Known Activations