© 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. 41834
    Prev
    Next
    INDEX
    Explanations

    material processing and treatment

    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
     their
    -1.51
     THRO
    -1.32
     \
    -1.26
    вЂ
    -1.26
    }}</
    -1.23
    Voltaje
    -1.21
     erec
    -1.18
    romeda
    -1.18
     exhib
    -1.17
     whose
    -1.16
    POSITIVE LOGITS
     oppure
    1.76
     it
    1.59
    เพื่อ
    1.50
    ١
    1.48
     atau
    1.45
     Umständen
    1.45
     reklama
    1.40
     Bagaimana
    1.39
    YOUR
    1.36
     alebo
    1.35
    Activations Density 0.333%

    No Known Activations