© 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. 27772
    Prev
    Next
    INDEX
    Explanations

    financials and revenue figures

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

    This neuron responds to numeric tokens, especially financial figures such as year-over-year percentages, dollar amounts, and other numbers.

    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
     our
    -1.17
    !!
    -1.09
     to
    -1.08
    ingat
    -1.05
     Landkreis
    -1.04
    alami
    -1.03
     very
    -1.01
     all
    -0.99
    egli
    -0.99
     loro
    -0.98
    POSITIVE LOGITS
     XXXIII
    1.21
     marseille
    1.18
     XXXVI
    1.16
     mexico
    1.15
    関連項目
    1.15
     dortmund
    1.13
    ount
    1.13
     Panorama
    1.11
     SKY
    1.11
    peka
    1.10
    Activations Density 0.009%

    No Known Activations