© 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. 123700
    Prev
    Next
    INDEX
    Explanations

    came across, discovered a, found the, learned how

    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
     then
    -1.84
     when
    -1.80
     since
    -1.69
     now
    -1.62
     to
    -1.55
     henceforth
    -1.32
     who
    -1.30
     today
    -1.29
     once
    -1.28
     in
    -1.26
    POSITIVE LOGITS
    日発売
    1.47
     two
    1.27
    läs
    1.25
    odiment
    1.24
    session
    1.23
     где
    1.23
     tinte
    1.22
     entera
    1.22
    cled
    1.21
     gdzie
    1.20
    Activations Density 0.030%

    No Known Activations