Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109
    Prev
    Next
    INDEX
    Explanations

    mortgage and note transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    дати
    -0.75
    gulier
    -0.73
    opter
    -0.71
    ффек
    -0.71
    CCP
    -0.70
     loung
    -0.70
    bigliamento
    -0.69
    ♐
    -0.69
    炭
    -0.68
     grate
    -0.68
    POSITIVE LOGITS
     mortgage
    1.67
     mortgages
    1.38
    mortgage
    1.23
     financing
    1.20
    balloon
    1.09
     Mortgage
    1.08
     secured
    1.08
    Mortgage
    1.05
     note
    0.96
     notes
    0.96
    Activations Density 0.021%

    No Known Activations