© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23879
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

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

    This neuron detects formatting separator lines and comment delimiters in code (e.g. “//”, “===”, “----”).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ☛
    -0.70
    bottomRight
    -0.68
     Frage
    -0.68
    トゥ
    -0.67
     domy
    -0.65
     ankaŭ
    -0.65
     discernible
    -0.64
    ⁽
    -0.64
     ingin
    -0.64
    ratie
    -0.63
    POSITIVE LOGITS
    bele
    0.75
     SRT
    0.72
     blessings
    0.72
     Indul
    0.71
     Babu
    0.71
     hạng
    0.69
     sculpt
    0.68
     IND
    0.68
    zzar
    0.68
     disappear
    0.67
    Activations Density 0.050%

    No Known Activations