© 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. 45393
    Prev
    Next
    INDEX
    Explanations

    order of operations

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

    The neuron is detecting definitional contexts—that is, “What is/are …?” questions and their corresponding definition or descriptive answer sentences.

    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
     kale
    -0.91
    👧
    -0.87
    ]^{\
    -0.87
    Gratis
    -0.87
    xxxx
    -0.83
     Michał
    -0.83
     türk
    -0.81
    教授
    -0.79
    annuation
    -0.79
     iLocal
    -0.79
    POSITIVE LOGITS
     laço
    0.89
     complexo
    0.89
     modeled
    0.87
     Traits
    0.86
     studied
    0.86
     Hered
    0.85
     farther
    0.83
     factors
    0.83
     heredity
    0.82
     któ
    0.82
    Activations Density 0.014%

    No Known Activations