© 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. 34-GEMMASCOPE-RES-131K
    7. 98852
    Prev
    Next
    INDEX
    Explanations

    indefinite articles

    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_34/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
     extremely
    -0.91
    several
    -0.91
     basada
    -0.91
     exceptionally
    -0.90
     exceptional
    -0.90
     some
    -0.89
     seleccionadas
    -0.88
     constituyen
    -0.86
     любом
    -0.85
     Things
    -0.85
    POSITIVE LOGITS
     a
    4.63
     isang
    1.62
     một
    1.57
     suatu
    1.51
     sebuah
    1.50
     एक
    1.46
     einer
    1.43
     een
    1.41
    一个
    1.39
     eine
    1.38
    Activations Density 0.129%

    No Known Activations