© 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. 34-GEMMASCOPE-RES-131K
    7. 64755
    Prev
    Next
    INDEX
    Explanations

    mortgage lenders and loans

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

    The neuron fires on occurrences of the word “mortgage” (and very strongly on that exact term wherever it appears).

    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
     takže
    -0.92
    isses
    -0.88
     Ciebie
    -0.85
    nancy
    -0.84
    reordered
    -0.84
    losseum
    -0.80
    stacle
    -0.79
    saucony
    -0.78
    besos
    -0.77
    gonia
    -0.77
    POSITIVE LOGITS
     mortgage
    1.18
     companies
    1.05
    holders
    1.05
     holder
    1.02
     brokers
    1.00
    Mortgage
    0.97
     prisoners
    0.97
     broker
    0.95
     Mortgage
    0.94
     Мор
    0.88
    Activations Density 0.008%

    No Known Activations