© 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. 22-GEMMASCOPE-RES-131K
    7. 35780
    Prev
    Next
    INDEX
    Explanations

    HTTP methods and accessors

    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_22/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
     to
    -1.37
    ernoo
    -1.34
     universitaire
    -1.34
     „
    -1.27
     Já
    -1.19
     seu
    -1.15
     tragé
    -1.14
     ۱۱
    -1.13
     tristes
    -1.07
     monstruos
    -1.04
    POSITIVE LOGITS
    あなたが
    1.22
     colorir
    1.21
     piattaforma
    1.16
     дешевле
    1.16
    )})
    1.15
     acolo
    1.13
    を目指す
    1.13
     cantit
    1.11
    他們
    1.11
    嘢
    1.10
    Activations Density 0.000%

    No Known Activations