© 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. 10-GEMMASCOPE-RES-131K
    7. 41206
    Prev
    Next
    INDEX
    Explanations

    academic publication identifiers

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

    The neuron fires on tokens that are part of technical reference identifiers—things like arXiv IDs, DOIs, URLs, and other citation strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    These
    -2.80
    This
    -2.67
    There
    -2.66
    Some
    -2.44
    They
    -2.36
    That
    -2.33
    What
    -2.28
     For
    -2.28
     It
    -2.27
    Those
    -2.27
    POSITIVE LOGITS
     lançado
    1.99
    蟊
    1.97
    '#
    1.88
     recentemente
    1.85
     発売
    1.84
    อื่น
    1.82
     atualmente
    1.81
    ing
    1.81
    アドバイス
    1.80
     война
    1.78
    Activations Density 0.001%

    No Known Activations