© 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. 34-GEMMASCOPE-RES-131K
    7. 30147
    Prev
    Next
    INDEX
    Explanations

    encode, write, read, AsString

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

    This neuron fires on code tokens naming data I/O or serialization operations (e.g. methods like Read, Write, Parse, encode, Serialize).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     read
    -1.41
    readInt
    -1.04
    อ่าน
    -1.03
     reading
    -0.95
     đọc
    -0.94
    未必
    -0.93
     PRACTICAL
    -0.93
    ריאה
    -0.92
     cuch
    -0.90
     reads
    -0.90
    POSITIVE LOGITS
     another
    0.94
     løs
    0.84
     hôtes
    0.81
    江
    0.80
     into
    0.79
     сильно
    0.77
     sacó
    0.77
     variés
    0.77
     October
    0.77
     reducing
    0.77
    Activations Density 0.003%

    No Known Activations