© 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. 13057
    Prev
    Next
    INDEX
    Explanations

    participate or affected

    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
    исленность
    -1.34
     sposo
    -1.32
     znaleźć
    -1.30
     acela
    -1.27
     acoged
    -1.27
     recevrez
    -1.26
     மற்ற
    -1.23
     ajutor
    -1.21
     chaqueta
    -1.18
     anderes
    -1.17
    POSITIVE LOGITS
     of
    2.97
     this
    1.40
     immen
    1.21
    0
    1.20
    chuhe
    1.18
    Rüyada
    1.18
    CAPITULO
    1.15
    нология
    1.14
    ytä
    1.13
    autoreleasepool
    1.12
    Activations Density 0.054%

    No Known Activations