© 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. 1963
    Prev
    Next
    INDEX
    Explanations

    bibliographic or search result components

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

    The neuron responds to numeric sequences—years, page numbers, IDs, and other digit-containing tokens in citations, URLs, and metadata.

    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
    仙
    -0.94
     alab
    -0.82
    割引
    -0.81
    giarism
    -0.81
     EDITORIAL
    -0.80
     توانید
    -0.79
    endphp
    -0.78
    CION
    -0.76
     확
    -0.75
    coço
    -0.74
    POSITIVE LOGITS
     Google
    1.48
    Google
    1.27
    Snippet
    1.06
    google
    1.02
     google
    1.00
    🟪
    0.91
    snippet
    0.90
     igjen
    0.86
    Kích
    0.86
    嫌弃
    0.85
    Activations Density 0.011%

    No Known Activations