© 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. 102731
    Prev
    Next
    INDEX
    Explanations

    word completion

    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
     is
    -1.18
    vielen
    -1.09
     mág
    -1.07
    提供了
    -1.06
     maneiras
    -1.05
    艄
    -1.05
     měli
    -1.05
     camere
    -1.04
     was
    -1.04
     lande
    -1.03
    POSITIVE LOGITS
     be
    2.42
     make
    1.59
     get
    1.47
     have
    1.47
     provide
    1.41
     take
    1.41
     develop
    1.38
     ולה
    1.35
     meet
    1.32
     perform
    1.29
    Activations Density 0.082%

    No Known Activations