© 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. 83745
    Prev
    Next
    INDEX
    Explanations

    home and garden spaces

    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
    ︕
    -2.53
    谂
    -2.38
    𖥧
    -2.38
    慊
    -2.31
    ครื่อง
    -2.30
    瑨
    -2.28
    '])->
    -2.27
    銫
    -2.25
    釹
    -2.25
    esserts
    -2.25
    POSITIVE LOGITS
     '
    3.41
    {
    2.61
     the
    2.53
     sole
    2.44
     einschließlich
    2.33
     w
    2.27
     flere
    2.22
    \
    2.19
    明显的
    2.17
     наше
    2.16
    Activations Density 0.003%

    No Known Activations