© 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. 98635
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
     ONLY
    -1.85
     only
    -1.84
     oddly
    -1.52
     noticeable
    -1.48
     unrelenting
    -1.46
     amusing
    -1.40
     resolute
    -1.40
     undeniably
    -1.40
     invigor
    -1.40
     immensely
    -1.38
    POSITIVE LOGITS
    を含
    1.52
    
    1.46
     -'
    1.45
     …..
    1.38
     .......
    1.34
     molti
    1.30
     мог
    1.29
    lication
    1.26
     is
    1.25
    __________
    1.24
    Activations Density 0.016%

    No Known Activations