© 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. 12790
    Prev
    Next
    INDEX
    Explanations

    advances in technology and medicine

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

    The neuron identifies the phrase "advances in" when discussing technological or scientific progress.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively activates on numeric tokens (quantities, measurements, years, percentages) in the text.

    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
     
    -2.58
    .
    -2.34
    )
    -2.03
     Another
    -1.86
    5
    -1.85
     inalámbrico
    -1.79
    на
    -1.77
    ឵
    -1.62
    3
    -1.61
    9
    -1.60
    POSITIVE LOGITS
     what
    2.14
     грудня
    2.05
    ᨆ
    1.94
     where
    1.90
     zatem
    1.86
     たく
    1.81
    卨
    1.80
     kutoka
    1.78
    镠
    1.78
     серпня
    1.77
    Activations Density 0.337%

    No Known Activations