© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104288
    Prev
    Next
    INDEX
    Explanations

    number and list items

    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
     soldadura
    -1.42
    czyć
    -1.39
     fisuras
    -1.38
     hlm
    -1.34
     sierpnia
    -1.34
     electricidad
    -1.34
     cejas
    -1.29
     espr
    -1.28
     burbuja
    -1.27
     both
    -1.26
    POSITIVE LOGITS
     is
    1.70
     was
    1.60
     were
    1.53
     the
    1.53
     були
    1.35
     
    1.34
     are
    1.32
    dens
    1.28
    Ahh
    1.27
     in
    1.23
    Activations Density 0.169%

    No Known Activations