© 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. 114191
    Prev
    Next
    INDEX
    Explanations

    routing and build commands

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "route" in programming contexts, particularly in web framework URL routing code.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
     and
    -1.63
     experimentado
    -1.52
     \&
    -1.48
     
    -1.43
     to
    -1.41
     vivido
    -1.41
     animado
    -1.38
     tomado
    -1.32
     we
    -1.30
     In
    -1.30
    POSITIVE LOGITS
    這個
    1.77
    ഒ
    1.67
    ഇ
    1.64
    Dengan
    1.46
    谖
    1.45
    说
    1.43
    되었습니다
    1.43
    Tidak
    1.42
     ghiaccio
    1.42
     入れ
    1.41
    Activations Density 0.002%

    No Known Activations