© 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. 39612
    Prev
    Next
    INDEX
    Explanations

    critically assessing scientific methods

    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
    したが
    -1.38
    了一個
    -1.23
    厕
    -1.23
     didn
    -1.19
     auriculares
    -1.13
     his
    -1.13
    -1.13
    车上
    -1.12
     agujero
    -1.11
     говорится
    -1.10
    POSITIVE LOGITS
     cautioned
    1.38
     epistem
    1.27
     parfois
    1.27
     مباراة
    1.24
     scientific
    1.22
     research
    1.19
     datasets
    1.18
     data
    1.18
    batis
    1.17
     científicas
    1.16
    Activations Density 0.148%

    No Known Activations