© 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. 22-GEMMASCOPE-RES-131K
    7. 35123
    Prev
    Next
    INDEX
    Explanations

    ratios and quantities

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

    The neuron specializes in spotting words that introduce or accompany numeric measurements or statistical data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    PÁG
    -1.00
    volves
    -0.96
     renovables
    -0.93
    ftal
    -0.93
     والع
    -0.92
     Humphries
    -0.91
     empie
    -0.88
    quisition
    -0.88
    Páginas
    -0.88
    quirer
    -0.88
    POSITIVE LOGITS
     one
    1.60
     each
    1.41
     하나
    1.12
    一つの
    1.07
     एक
    1.05
     ఒ
    1.00
     вместе
    1.00
     один
    0.99
    同一
    0.99
    一个
    0.98
    Activations Density 0.116%

    No Known Activations