© 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. 102347
    Prev
    Next
    INDEX
    Explanations

    matrices, eigenvalues, characteristic polynomial

    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
     servicios
    -1.33
     tarjeta
    -1.27
     tarjetas
    -1.26
    ﻷ
    -1.24
     кровать
    -1.22
     июня
    -1.18
    ʼn
    -1.18
     método
    -1.18
     Substanz
    -1.18
    criteria
    -1.17
    POSITIVE LOGITS
     isolamento
    1.52
    när
    1.45
    från
    1.33
     surabaya
    1.30
     bakar
    1.27
    Bisa
    1.27
    مقدمه
    1.25
     semarang
    1.24
     bandung
    1.23
    Ecole
    1.23
    Activations Density 0.187%

    No Known Activations