© 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. 72079
    Prev
    Next
    INDEX
    Explanations

    company funding and investment

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

    This neuron detects numeric tokens that represent monetary amounts in funding or financial contexts.

    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
     there
    -1.57
    使用方法
    -1.55
    There
    -1.50
    引用元
    -1.48
     decât
    -1.37
    を進
    -1.37
    Not
    -1.35
    
    -1.34
    を選択
    -1.34
     if
    -1.34
    POSITIVE LOGITS
     La
    1.33
    IsMutable
    1.30
    лася
    1.26
     möjligt
    1.25
    anese
    1.23
     LA
    1.23
     attractiveness
    1.22
    欒
    1.21
    Biographies
    1.20
     faktiskt
    1.20
    Activations Density 0.020%

    No Known Activations