© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85725
    Prev
    Next
    INDEX
    Explanations

    technical compound terms

    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
    -2.23
     one
    -1.92
     after
    -1.88
     that
    -1.87
     these
    -1.80
     kept
    -1.79
     those
    -1.77
     will
    -1.77
     this
    -1.74
     keep
    -1.74
    POSITIVE LOGITS
    without
    1.62
     senza
    1.55
    Metode
    1.54
     pere
    1.44
    Zna
    1.43
    Aktu
    1.42
    Zdrav
    1.41
    你不要
    1.38
    Reklama
    1.38
     intrig
    1.38
    Activations Density 0.462%

    No Known Activations