© 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. 38681
    Prev
    Next
    INDEX
    Explanations

    official bodies and documents

    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
     only
    -1.71
    ablemente
    -1.38
     if
    -1.35
    Some
    -1.35
     vermutlich
    -1.34
    They
    -1.33
     at
    -1.27
    Often
    -1.27
    Sometimes
    -1.26
     بعض
    -1.24
    POSITIVE LOGITS
     such
    1.42
     idag
    1.38
    
    1.31
     ciò
    1.31
    崀
    1.30
     rappeler
    1.27
    廰
    1.27
    Avec
    1.26
     distribuição
    1.23
     SUCH
    1.21
    Activations Density 0.153%

    No Known Activations