© 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. 22-GEMMASCOPE-RES-131K
    7. 65709
    Prev
    Next
    INDEX
    Explanations

    each, every, per

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

    The neuron activates on numeric tokens—counts, measurements, percentages, dollar amounts, dates, and other statistical figures—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_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
     it
    -0.98
     or
    -0.92
    wieś
    -0.91
    client
    -0.91
    <0xBE>
    -0.84
     temos
    -0.80
    bmod
    -0.80
     hasta
    -0.79
     had
    -0.79
    ʈ
    -0.79
    POSITIVE LOGITS
     each
    2.14
    每个
    1.89
    每个人
    1.80
     каждого
    1.66
     لكل
    1.64
     každého
    1.57
    每個
    1.55
     mỗi
    1.42
    each
    1.35
    EACH
    1.31
    Activations Density 0.046%

    No Known Activations