© 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. 42133
    Prev
    Next
    INDEX
    Explanations

    around on or in

    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
     that
    -2.45
    That
    -1.71
     then
    -1.67
    滬
    -1.54
     this
    -1.52
     its
    -1.52
     two
    -1.49
     in
    -1.48
    With
    -1.48
     This
    -1.46
    POSITIVE LOGITS
    </strong>
    1.70
     ;
    1.52
    ferred
    1.47
     AROUND
    1.45
     fréquent
    1.42
     brillantes
    1.41
    initWith
    1.38
    orted
    1.38
     вокруг
    1.37
     celé
    1.37
    Activations Density 0.028%

    No Known Activations