© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42954
    Prev
    Next
    INDEX
    Explanations

    bankruptcy and insolvency proceedings

    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
    vamo
    -1.52
     détaillés
    -1.34
    ств
    -1.23
     decât
    -1.23
     than
    -1.23
     tena
    -1.21
    opheles
    -1.17
    ಯ
    -1.16
     kind
    -1.15
    sellor
    -1.15
    POSITIVE LOGITS
     it
    1.50
     basado
    1.25
     sabía
    1.23
     値下げ
    1.23
     السياس
    1.23
    将其
    1.23
     женщины
    1.23
     juiste
    1.21
     綺麗
    1.19
     düşük
    1.19
    Activations Density 0.056%

    No Known Activations