© 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. 47495
    Prev
    Next
    INDEX
    Explanations

    importance of

    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
     respiración
    -1.68
     kanskje
    -1.55
     many
    -1.55
     spesielt
    -1.50
     about
    -1.47
     some
    -1.39
     veldig
    -1.38
     ferdig
    -1.37
     elevada
    -1.36
    imbawa
    -1.36
    POSITIVE LOGITS
     of
    2.25
     and
    1.33
    tierten
    1.28
     ครับ
    1.25
     大きい
    1.23
     considération
    1.23
     ouvrage
    1.23
     then
    1.21
    gebiete
    1.21
     cadeau
    1.20
    Activations Density 0.035%

    No Known Activations