© 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. 65472
    Prev
    Next
    INDEX
    Explanations

    dining or diners

    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
    姈
    -2.98
    ing
    -2.89
    觔
    -2.80
    </h4>
    -2.72
     \
    -2.67
     CYTHON
    -2.59
    iocene
    -2.56
    𖥧
    -2.55
    轫
    -2.50
    ază
    -2.45
    POSITIVE LOGITS
    of
    2.98
    -
    2.44
    {
    2.16
     But
    2.14
     של
    2.13
     dine
    2.13
    うわ
    2.11
    诞生
    2.08
    (
    2.06
    賔
    2.00
    Activations Density 0.001%

    No Known Activations