© 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. 47630
    Prev
    Next
    INDEX
    Explanations

    programming class names and method calls

    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
     new
    -1.99
     Surprisingly
    -1.67
     their
    -1.66
     Nearly
    -1.63
     an
    -1.61
     one
    -1.60
     Without
    -1.60
     ALWAYS
    -1.59
     exuberant
    -1.58
     unrelenting
    -1.57
    POSITIVE LOGITS
     then
    1.78
    菒
    1.75
     that
    1.66
     затем
    1.63
    
    1.58
     of
    1.56
    ⩕
    1.55
    敺
    1.52
     paloma
    1.50
     таких
    1.45
    Activations Density 0.033%

    No Known Activations