© 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. 353
    Prev
    Next
    INDEX
    Explanations

    titles and headings

    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
    ﮨ
    -2.95
    ጺ
    -2.64
     Vorschläge
    -2.64
    뮐
    -2.61
    觧
    -2.61
    鯓
    -2.48
    Ꮷ
    -2.45
    းက
    -2.44
    鰨
    -2.44
    阄
    -2.41
    POSITIVE LOGITS
    </strong>
    2.75
    {
    2.02
     среднего
    2.00
     有
    1.98
     marvel
    1.96
     *
    1.92
    であった
    1.90
     
    1.89
     самый
    1.86
     できる
    1.84
    Activations Density 0.000%

    No Known Activations