© 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. 42113
    Prev
    Next
    INDEX
    Explanations

    <?xml declaration

    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
     their
    -2.06
     because
    -2.02
     your
    -2.02
    。』
    -1.87
     as
    -1.85
     '
    -1.80
    驺
    -1.80
    穑
    -1.74
    两天
    -1.73
    遄
    -1.73
    POSITIVE LOGITS
    ד
    2.25
    {
    2.16
     Перейти
    2.06
    ędzynarod
    1.97
    蔘
    1.89
     '\''
    1.85
    چی
    1.84
     этой
    1.78
    This
    1.77
     エ
    1.77
    Activations Density 0.002%

    No Known Activations