© 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. 54024
    Prev
    Next
    INDEX
    Explanations

    page numbers and identifiers

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

    The neuron consistently fires on capitalized identifiers (class, type, or namespace names) in 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_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
    ená
    -0.84
     сало
    -0.82
     Corolla
    -0.81
    acen
    -0.81
     zeros
    -0.80
    decer
    -0.80
    ený
    -0.79
    榄
    -0.79
    矚
    -0.77
    essional
    -0.77
    POSITIVE LOGITS
     Page
    1.11
    Page
    1.06
     page
    0.85
     PAGE
    0.79
    Daniel
    0.77
     Daniels
    0.75
    Bound
    0.70
    ページ
    0.69
     Daniel
    0.69
    座位
    0.69
    Activations Density 0.007%

    No Known Activations