© 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. 93113
    Prev
    Next
    INDEX
    Explanations

    mortgage rates discounts

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

    The main thing this neuron does is detect numbers (numeric sequences) in the text.

    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
    δυ
    -0.79
    🟡
    -0.74
     Alden
    -0.72
     Wydawnictwo
    -0.71
    ङ
    -0.71
    дмила
    -0.70
     sper
    -0.69
    ماه
    -0.68
     Lub
    -0.67
    🎢
    -0.67
    POSITIVE LOGITS
     mortgage
    1.23
     redraw
    0.93
     servic
    0.93
    Mortgage
    0.89
     residential
    0.86
     Mortgage
    0.85
    mortgage
    0.84
     Loan
    0.81
     loan
    0.81
     hardship
    0.78
    Activations Density 0.006%

    No Known Activations