© 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. 34-GEMMASCOPE-RES-131K
    7. 47030
    Prev
    Next
    INDEX
    Explanations

    financial markets and analysis

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

    The neuron strongly activates on headline or section-title tokens (e.g. multiword titles and their punctuation) rather than regular sentence text.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Werde
    -0.88
    Grüsse
    -0.87
    ಗ
    -0.84
    IARC
    -0.84
    記者
    -0.83
     IDEOGRAPH
    -0.83
    Herzliche
    -0.80
    ன
    -0.80
    因為
    -0.78
     standen
    -0.78
    POSITIVE LOGITS
     charts
    1.24
    MACRO
    1.20
     strategist
    1.16
     markets
    1.13
     makro
    1.12
     investors
    1.10
     macro
    1.10
     bond
    1.10
     ETF
    1.10
     Charts
    1.07
    Activations Density 0.060%

    No Known Activations