© 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. 15589
    Prev
    Next
    INDEX
    Explanations

    noun followed by verb

    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
    Negative Logits
     and
    -2.89
     to
    -2.22
     that
    -1.75
    좆
    -1.68
    ertia
    -1.66
     \
    -1.65
    注意事
    -1.62
    糨
    -1.61
     "
    -1.60
     
    -1.60
    POSITIVE LOGITS
    8
    2.92
    2
    2.83
    0
    2.80
    9
    2.75
    5
    2.72
    7
    2.67
    4
    2.50
    3
    2.42
    1
    2.39
    6
    2.34
    Activations Density 0.495%

    No Known Activations