© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15650
    Prev
    Next
    INDEX
    Explanations

    sales of goods

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

    The neuron spotlights numeric expressions and quantitative figures—especially monetary amounts, sales/statistics, and other numbers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     still
    -1.15
    anoia
    -1.12
     []:
    -1.10
    libft
    -1.09
     &___
    -1.08
     who
    -1.07
    :]
    -1.07
    zędu
    -1.05
    Publica
    -1.05
    את
    -1.04
    POSITIVE LOGITS
     sueño
    1.13
     financière
    1.07
     for
    1.07
     eivät
    1.06
    Their
    1.05
     değildir
    1.04
    で使用
    1.03
    abaret
    1.02
    Donde
    1.02
    servicios
    1.01
    Activations Density 0.048%

    No Known Activations