© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128465
    Prev
    Next
    INDEX
    Explanations

    scientific study or modeling

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

    technical and scientific content related to water systems, hydrology, and environmental measurements.

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

    The neuron mainly detects numeric values and numerical expressions (e.g., measurements, quantities, and statistics).

    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
    
    -2.09
     effectuer
    -1.66
    噱
    -1.64
     contenidos
    -1.59
    Elő
    -1.59
     specif
    -1.58
    
    -1.53
    ごめん
    -1.52
     astounding
    -1.51
    킁
    -1.50
    POSITIVE LOGITS
     for
    2.11
     all
    1.80
     with
    1.73
     if
    1.71
     usually
    1.65
     featuring
    1.59
     has
    1.56
     will
    1.55
     during
    1.53
     some
    1.51
    Activations Density 0.028%

    No Known Activations