© 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. 34-GEMMASCOPE-RES-131K
    7. 57501
    Prev
    Next
    INDEX
    Explanations

    find symbol, called when, designated initializer

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

    This neuron fires on comment‐block summary phrases in source code documentation (e.g. “Called when…” or “The main entry point…”).

    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
    紫色
    -0.90
    endaftar
    -0.84
    クト
    -0.83
    curkan
    -0.82
     Durchschnitt
    -0.76
    zegor
    -0.76
     sillä
    -0.75
    ervos
    -0.75
     risa
    -0.74
    مد
    -0.73
    POSITIVE LOGITS
     године
    1.08
     Variables
    0.88
    isible
    0.85
     initComponents
    0.82
     EXIT
    0.81
    Verifier
    0.80
     void
    0.79
    fdf
    0.78
    Exit
    0.77
    barred
    0.77
    Activations Density 0.001%

    No Known Activations