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. 8484
    Prev
    Next
    INDEX
    Explanations

    taxation, payments, and obligations

    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
    isième
    -1.03
    美子
    -0.94
    садки
    -0.91
    此事
    -0.86
    公布
    -0.85
    zenz
    -0.85
    是什么
    -0.84
     ghastly
    -0.83
     tamu
    -0.82
     cabal
    -0.82
    POSITIVE LOGITS
     obligations
    1.22
    paying
    1.18
     on
    1.17
     obligation
    1.09
     paiement
    1.05
    paid
    1.05
     liability
    1.04
     laws
    1.04
    laws
    1.03
     levied
    1.02
    Activations Density 0.012%

    No Known Activations