© 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. 127519
    Prev
    Next
    INDEX
    Explanations

    * sequences

    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
    Not in Any Lists

    No Comments

    Negative Logits
     capabilities
    -1.55
     azar
    -1.49
     meines
    -1.47
    ficulties
    -1.39
     montar
    -1.38
    <bos>
    -1.38
    tedì
    -1.37
    ?
    -1.33
    \
    -1.33
     Arxivat
    -1.32
    POSITIVE LOGITS
    ться
    1.68
     ciertos
    1.58
     ciertas
    1.55
     they
    1.55
     débuts
    1.50
     توضی
    1.48
     cierta
    1.45
     eléctricas
    1.38
     algunas
    1.38
     оригі
    1.35
    Activations Density 0.009%

    No Known Activations