© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90610
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

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

    This neuron detects boilerplate code metadata tokens—things like license‐header keywords and package/import namespace names.

    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
     diamonds
    -0.91
     Meksiko
    -0.85
     kotak
    -0.84
     imprimée
    -0.82
     Pues
    -0.81
    Смотрите
    -0.81
     medis
    -0.79
     Horas
    -0.79
     balas
    -0.79
     sakin
    -0.79
    POSITIVE LOGITS
    cantara
    0.80
    antart
    0.78
     ceea
    0.76
    Médaille
    0.75
    ニメ
    0.74
     session
    0.74
     Darauf
    0.73
    ategorised
    0.73
    session
    0.72
    hpp
    0.72
    Activations Density 0.000%

    No Known Activations