© 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. 6935
    Prev
    Next
    INDEX
    Explanations

    actors' last names

    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
    哙
    -1.38
     увиде
    -1.26
     работают
    -1.24
     eenen
    -1.24
     хоте
    -1.21
    c
    -1.18
    ucle
    -1.17
    媵
    -1.15
    点点头
    -1.14
     pfle
    -1.13
    POSITIVE LOGITS
     masih
    1.36
     hvordan
    1.16
     the
    1.15
     sekarang
    1.14
     abund
    1.14
    </tfoot>
    1.13
    特朗普
    1.12
    董事长
    1.10
    ularity
    1.09
     уже
    1.09
    Activations Density 0.080%

    No Known Activations