© 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. 47267
    Prev
    Next
    INDEX
    Explanations

    method, judge, distribute

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

    The neuron activates whenever it sees a “METHOD” declaration label in code (i.e. the token “method” marking a function/method definition).

    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
    いつもの
    -0.82
    bohemian
    -0.79
     extensive
    -0.75
    extensive
    -0.74
    üstü
    -0.74
     ignorance
    -0.73
    tése
    -0.73
    itai
    -0.72
     causado
    -0.72
     conseillé
    -0.72
    POSITIVE LOGITS
     pointer
    0.91
    isi
    0.83
    PhysRevD
    0.82
     malaria
    0.80
     cruelty
    0.79
    Ārējās
    0.77
    Pointer
    0.77
    Phys
    0.77
     glos
    0.76
     seeker
    0.74
    Activations Density 0.001%

    No Known Activations