© 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. 22668
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, functions, space

    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
     These
    -1.78
    These
    -1.70
     queste
    -1.52
     estos
    -1.52
     They
    -1.48
     Эти
    -1.41
    CIÓN
    -1.40
     these
    -1.36
     it
    -1.29
    烙
    -1.28
    POSITIVE LOGITS
    odles
    1.43
     seulement
    1.41
    stalgia
    1.23
     internas
    1.19
     vitesse
    1.19
    pois
    1.19
     permitiendo
    1.13
     seule
    1.13
    nourished
    1.13
     only
    1.12
    Activations Density 0.044%

    No Known Activations