© 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. 34-GEMMASCOPE-RES-131K
    7. 117466
    Prev
    Next
    INDEX
    Explanations

    maximum measurements or quantities

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

    The neuron is specialized to detect numeric expressions (digits, number words, and related quantity terms) 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_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
     nästan
    -0.84
     feveral
    -0.83
    mHandler
    -0.82
     presque
    -0.79
     thofe
    -0.79
     adet
    -0.79
    nearly
    -0.78
    OLUTION
    -0.76
     Pontific
    -0.75
     barbar
    -0.73
    POSITIVE LOGITS
     maximum
    5.63
     max
    4.78
     макси
    4.53
    maximum
    4.53
     máximo
    4.50
    Maximum
    4.03
     Maximum
    4.00
    max
    3.94
     MAXIMUM
    3.70
    最多
    3.66
    Activations Density 0.145%

    No Known Activations