© 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. 1888
    Prev
    Next
    INDEX
    Explanations

    Spanish verbs preterite

    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
     it
    -2.02
     a
    -1.85
     this
    -1.80
     what
    -1.60
     that
    -1.60
     has
    -1.51
    それは
    -1.45
    In
    -1.42
     which
    -1.42
     substantially
    -1.41
    POSITIVE LOGITS
    泚
    1.68
    archiwizowane
    1.66
     decidieron
    1.63
     cuentan
    1.60
     lograron
    1.59
     empezaron
    1.58
     habrían
    1.55
     hubieran
    1.55
     dejaron
    1.54
     recibieron
    1.53
    Activations Density 0.214%

    No Known Activations