© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72210
    Prev
    Next
    INDEX
    Explanations

    questions starting with why

    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
    Negative Logits
    曁
    -1.73
    vestres
    -1.53
    ⟣
    -1.49
    viève
    -1.41
     marcas
    -1.41
    Cuánt
    -1.38
     prepping
    -1.38
    更何况
    -1.35
     если
    -1.34
     ее
    -1.34
    POSITIVE LOGITS
     why
    2.20
     蝶
    1.35
     this
    1.30
    Reasons
    1.30
    bruik
    1.29
     lagerfeld
    1.29
    your
    1.27
     女生
    1.27
     sám
    1.26
     these
    1.25
    Activations Density 0.044%

    No Known Activations