© 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. 131066
    Prev
    Next
    INDEX
    Explanations

    header file imports or directives

    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
     spezi
    -1.48
    bably
    -1.44
     verhind
    -1.37
    catálogo
    -1.34
     talvez
    -1.32
     favorece
    -1.27
     hatta
    -1.27
    鳏
    -1.25
    因为他
    -1.25
     are
    -1.23
    POSITIVE LOGITS
     these
    1.44
    www
    1.39
     también
    1.25
    ätigung
    1.24
     like
    1.23
     PUSTAKA
    1.23
     Since
    1.23
     this
    1.21
     säga
    1.21
     people
    1.20
    Activations Density 0.095%

    No Known Activations