© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11948
    Prev
    Next
    INDEX
    Explanations

    cash transactions and auditing

    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
     sourcing
    -0.75
     nicio
    -0.74
    ('./
    -0.72
     kontaktu
    -0.71
     barva
    -0.71
    畳
    -0.71
     medir
    -0.69
     Contracts
    -0.69
    setPadding
    -0.69
     wissenschaft
    -0.69
    POSITIVE LOGITS
     cash
    1.69
     reconciliation
    1.41
     recaudación
    1.31
     collections
    1.24
     Reconciliation
    1.24
    cash
    1.23
     daily
    1.23
     reconcile
    1.19
    daily
    1.16
     money
    1.13
    Activations Density 0.017%

    No Known Activations