© 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. 21840
    Prev
    Next
    INDEX
    Explanations

    widespread use or availability

    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
    reszcie
    -1.46
     that
    -1.40
     my
    -1.31
    celotti
    -1.27
     bañera
    -1.26
    мор
    -1.25
     rám
    -1.21
    nicity
    -1.19
     still
    -1.19
     should
    -1.19
    POSITIVE LOGITS
    Здравствуйте
    1.57
    Всем
    1.33
     作り方
    1.30
     گست
    1.20
    Buenas
    1.20
    8
    1.18
    Ответы
    1.16
    Their
    1.16
    Earlier
    1.15
    Скачать
    1.15
    Activations Density 0.152%

    No Known Activations