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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59635
    Prev
    Next
    INDEX
    Explanations

    explains "the" followed by a noun

    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
    -2.09
    ā
    -1.54
     två
    -1.36
     gese
    -1.35
    liebe
    -1.32
    about
    -1.28
    \-
    -1.26
    different
    -1.26
     født
    -1.24
    IVENESS
    -1.23
    POSITIVE LOGITS
     there
    1.71
     ponieważ
    1.63
     gdyż
    1.59
     you
    1.56
     زیرا
    1.49
     same
    1.48
     it
    1.45
     humedad
    1.43
    並沒有
    1.42
     dlatego
    1.41
    Activations Density 0.165%

    No Known Activations