© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92673
    Prev
    Next
    INDEX
    Explanations

    d/dx derivatives and fractions

    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_34/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
     disediakan
    -0.94
     Dias
    -0.93
     dipilih
    -0.91
    Dias
    -0.90
     Daylight
    -0.89
     牙
    -0.85
     airpods
    -0.85
     diterapkan
    -0.84
     scolaires
    -0.84
     économiques
    -0.82
    POSITIVE LOGITS
     d
    4.53
    d
    2.81
     д
    2.30
    ｄ
    1.70
    𝑑
    1.63
     D
    1.56
     د
    1.55
     ד
    1.28
     dd
    1.28
    getD
    1.26
    Activations Density 0.147%

    No Known Activations