© 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. 114110
    Prev
    Next
    INDEX
    Explanations

    code syntax or descriptive text

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

    comments or documentation lines in source code, particularly inline comments and descriptive text within code files.

    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
     nationales
    -1.56
     hanya
    -1.55
    …»
    -1.52
    ...»
    -1.50
    sibles
    -1.43
     artikel
    -1.43
    !»
    -1.39
    »?
    -1.38
     radikal
    -1.37
    靫
    -1.36
    POSITIVE LOGITS
     that
    1.77
     from
    1.71
     such
    1.63
     how
    1.55
     or
    1.54
     longtime
    1.52
     things
    1.48
     so
    1.43
     increasing
    1.40
     for
    1.39
    Activations Density 0.000%

    No Known Activations