© 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. 34-GEMMASCOPE-RES-131K
    7. 84832
    Prev
    Next
    INDEX
    Explanations

    scroll open, menu open

    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_34/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
     rafraî
    -1.59
     humeur
    -1.40
     réjou
    -1.35
     régal
    -1.34
     surpren
    -1.31
     Kelas
    -1.27
    Hvis
    -1.27
     Makanan
    -1.24
     amélior
    -1.24
     éton
    -1.23
    POSITIVE LOGITS
     develop
    1.27
     all
    1.13
     by
    1.13
     before
    1.09
     when
    1.09
     with
    1.05
     or
    1.03
     reduce
    1.02
     many
    1.02
     each
    1.01
    Activations Density 0.087%

    No Known Activations