© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66281
    Prev
    Next
    INDEX
    Explanations

    code involving false or none

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

    This neuron fires on statement terminators—specifically the semicolon ending lines of code.

    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
    QUOT
    -1.02
     vedea
    -0.92
    Leírás
    -0.92
     específicos
    -0.90
     chaleureux
    -0.89
     garantit
    -0.89
    зирован
    -0.89
     décontract
    -0.88
     spécialement
    -0.85
     Grimal
    -0.85
    POSITIVE LOGITS
     if
    1.15
     If
    0.92
     either
    0.82
     should
    0.81
    if
    0.80
     Бога
    0.79
    PACS
    0.76
     into
    0.75
     seem
    0.73
    cations
    0.73
    Activations Density 0.029%

    No Known Activations