© 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. 15516
    Prev
    Next
    INDEX
    Explanations

    programming library types

    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
     ALWAYS
    -1.67
     one
    -1.66
     \
    -1.63
    One
    -1.56
     einer
    -1.50
    An
    -1.48
     Usually
    -1.45
     to
    -1.41
     einem
    -1.37
    :
    -1.36
    POSITIVE LOGITS
     that
    2.14
     certificación
    1.70
     importación
    1.63
     dieß
    1.62
     flexibilidad
    1.59
     graduación
    1.56
    
    1.55
     fabricación
    1.54
     espalda
    1.54
     затем
    1.52
    Activations Density 0.004%

    No Known Activations