© 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. 11978
    Prev
    Next
    INDEX
    Explanations

    assigning values or properties

    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
     kenal
    -1.60
     tropicales
    -1.59
    ♪♪
    -1.58
    nof
    -1.55
     אחרים
    -1.54
     kutu
    -1.53
    zule
    -1.52
     farine
    -1.47
    ನ್
    -1.46
    depends
    -1.45
    POSITIVE LOGITS
     need
    1.94
     use
    1.77
     needed
    1.77
     necessary
    1.65
     также
    1.63
     Another
    1.60
     can
    1.57
     was
    1.56
     gets
    1.53
     -
    1.52
    Activations Density 0.001%

    No Known Activations