© 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. 73050
    Prev
    Next
    INDEX
    Explanations

    academic research and studies

    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
    🕗
    -1.73
     不是
    -1.66
    淆
    -1.58
    𓇼
    -1.57
    ⑊
    -1.54
    ंटर
    -1.45
     Gives
    -1.45
     Placing
    -1.44
     Otherwise
    -1.43
    شفى
    -1.43
    POSITIVE LOGITS
    ?“
    1.80
    j
    1.60
    no
    1.52
     vigorously
    1.52
    il
    1.49
     たま
    1.48
    ?”
    1.46
     способ
    1.41
    os
    1.40
     dieren
    1.38
    Activations Density 0.045%

    No Known Activations