© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1844
    Prev
    Next
    INDEX
    Explanations

    more adjective

    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
     of
    -2.81
     on
    -2.41
     for
    -2.14
    :
    -2.02
     because
    -2.00
     in
    -1.91
     to
    -1.88
     it
    -1.86
     this
    -1.84
     then
    -1.79
    POSITIVE LOGITS
    LEncoder
    1.84
     visant
    1.77
     soldadura
    1.77
     medición
    1.75
     pieles
    1.73
     rehabilitación
    1.70
     communs
    1.68
    ophanes
    1.67
     meditación
    1.66
    ibatkan
    1.65
    Activations Density 0.046%

    No Known Activations