© 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. 58176
    Prev
    Next
    INDEX
    Explanations

    LT prefix 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
    Negative Logits
    lgari
    -2.69
    
    -2.66
     sikap
    -2.41
    umbnail
    -2.39
    柃
    -2.34
     "")
    -2.33
    ेमाल
    -2.28
    C
    -2.27
    龊
    -2.23
    鋮
    -2.23
    POSITIVE LOGITS
    \
    3.28
    3
    3.25
    1
    3.23
    9
    3.20
    4
    2.95
    8
    2.95
     jarring
    2.91
     '
    2.72
    6
    2.66
    5
    2.61
    Activations Density 0.005%

    No Known Activations