© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127623
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    
    -1.95
     concevoir
    -1.89
     公園
    -1.72
    through
    -1.66
     humbling
    -1.65
     gérer
    -1.64
     GRAHAM
    -1.60
     reconnaître
    -1.59
    gled
    -1.58
    dzić
    -1.57
    POSITIVE LOGITS
     accustomed
    2.05
     Many
    1.77
     ihr
    1.69
    j
    1.66
    是非常
    1.65
     специалисты
    1.65
    c
    1.63
     Both
    1.63
     additionally
    1.63
    INTAIN
    1.62
    Activations Density 0.003%

    No Known Activations