© 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. 62896
    Prev
    Next
    INDEX
    Explanations

    numbers and statistical data

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

    The neuron activates on numeric tokens—years, percentages, measurements, and other digits conveying statistical or quantitative 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_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
     simply
    -0.82
     simplemente
    -0.81
     just
    -0.81
    读书
    -0.79
     numberOfRows
    -0.78
    pire
    -0.77
    rense
    -0.77
    lovakia
    -0.75
     slit
    -0.74
    bons
    -0.73
    POSITIVE LOGITS
     hierdie
    0.84
     kopf
    0.82
     escudo
    0.82
    fw
    0.82
     coffre
    0.81
     nzuri
    0.81
     郭
    0.81
    Ṁ
    0.81
    音が
    0.81
     PubMed
    0.81
    Activations Density 0.003%

    No Known Activations