© 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. 98881
    Prev
    Next
    INDEX
    Explanations

    programming library components

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

    The neuron is triggered by programming identifiers and symbols—especially names of imported modules, classes, functions, and other capitalized code tokens in source files.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
     progettazione
    -1.13
     malattia
    -1.13
     giocare
    -1.09
    了许多
    -1.07
     esigen
    -1.04
     manutenzione
    -1.03
     рассказала
    -1.02
    🎦
    -1.02
     Narr
    -1.02
     tiež
    -1.00
    POSITIVE LOGITS
     are
    1.37
     that
    1.31
     some
    1.23
     séries
    1.21
     Վերցված
    1.20
     Some
    1.16
    newGame
    1.16
     jugend
    1.15
     these
    1.14
    Some
    1.14
    Activations Density 0.135%

    No Known Activations