© 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. 22-GEMMASCOPE-RES-131K
    7. 32767
    Prev
    Next
    INDEX
    Explanations

    programming imports or libraries

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     its
    -1.36
     envía
    -1.26
     miesto
    -1.26
     ilumina
    -1.23
     the
    -1.23
     necessarie
    -1.20
     với
    -1.19
     importanti
    -1.19
     añade
    -1.18
     cierra
    -1.18
    POSITIVE LOGITS
    <bos>
    1.24
    但却
    1.09
    但这
    1.07
    Према
    1.06
     hvem
    1.05
    脍
    1.02
    Кроме
    1.01
    編曲
    1.00
     kain
    0.96
     hvilke
    0.96
    Activations Density 0.023%

    No Known Activations