© 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. 42083
    Prev
    Next
    INDEX
    Explanations

    conditional logic

    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
     as
    -1.79
     now
    -1.43
    _
    -1.41
     would
    -1.39
     although
    -1.35
     first
    -1.33
    šanu
    -1.33
    了一个
    -1.32
     only
    -1.27
    階段
    -1.27
    POSITIVE LOGITS
     the
    1.57
    徜
    1.48
    大きな
    1.32
    帰って
    1.32
     verschillende
    1.31
     verur
    1.30
     大き
    1.28
     Auflösung
    1.27
     gespeichert
    1.21
     it
    1.19
    Activations Density 0.074%

    No Known Activations