© 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. 15805
    Prev
    Next
    INDEX
    Explanations

    MAHU, Mabuya, mabel, MAB, vs

    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
    翾
    -2.36
    ,
    -2.23
    ÑO
    -2.02
    "،
    -1.97
    .
    -1.90
    ’
    -1.90
    🌀
    -1.88
     turístico
    -1.88
     navegando
    -1.84
     itſelf
    -1.81
    POSITIVE LOGITS
    and
    2.45
     haupts
    2.34
    および
    2.30
     использование
    2.16
     ehemaligen
    1.96
     και
    1.95
     «
    1.92
     rejoice
    1.88
     akin
    1.83
     работают
    1.81
    Activations Density 0.070%

    No Known Activations