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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72142
    Prev
    Next
    INDEX
    Explanations

    code initialization

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

    This neuron detects code declaration tokens—e.g. keywords and identifiers that introduce classes, functions/methods, constructors, or other definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    vább
    -1.09
     Tuttavia
    -1.06
     pokra
    -1.05
    Tämä
    -1.04
    felizmente
    -1.02
    SearchTree
    -1.02
     that
    -1.01
    ależy
    -1.00
     pokrač
    -1.00
     other
    -0.98
    POSITIVE LOGITS
     introductory
    1.08
    Introductory
    1.06
    一開始
    1.01
     început
    0.98
     overview
    0.95
    แรก
    0.93
    开头
    0.93
    liano
    0.92
    初始
    0.91
     initialization
    0.90
    Activations Density 0.019%

    No Known Activations